47 results on '"Chao, Wei-Lun"'
Search Results
2. Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networks
- Author
-
Elhamod, Mohannad, Khurana, Mridul, Manogaran, Harish Babu, Uyeda, Josef C., Balk, Meghan A., Dahdul, Wasila, Bakış, Yasin, Bart, Henry L., Mabee, Paula M., Lapp, Hilmar, Balhoff, James P., Charpentier, Caleb, Carlyn, David, Chao, Wei-Lun, Stewart, Charles V., Rubenstein, Daniel I., Berger-Wolf, Tanya, and Karpatne, Anuj
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer Vision and Pattern Recognition (cs.CV) ,Image and Video Processing (eess.IV) ,FOS: Electrical engineering, electronic engineering, information engineering ,Computer Science - Computer Vision and Pattern Recognition ,Electrical Engineering and Systems Science - Image and Video Processing ,Machine Learning (cs.LG) - Abstract
Discovering evolutionary traits that are heritable across species on the tree of life (also referred to as a phylogenetic tree) is of great interest to biologists to understand how organisms diversify and evolve. However, the measurement of traits is often a subjective and labor-intensive process, making trait discovery a highly label-scarce problem. We present a novel approach for discovering evolutionary traits directly from images without relying on trait labels. Our proposed approach, Phylo-NN, encodes the image of an organism into a sequence of quantized feature vectors -- or codes -- where different segments of the sequence capture evolutionary signals at varying ancestry levels in the phylogeny. We demonstrate the effectiveness of our approach in producing biologically meaningful results in a number of downstream tasks including species image generation and species-to-species image translation, using fish species as a target example.
- Published
- 2023
3. Improving Pancreatic Cyst Management: Artificial Intelligence-Powered Prediction of Advanced Neoplasms through Endoscopic Ultrasound-Guided Confocal Endomicroscopy.
- Author
-
Jiang, Joanna, Chao, Wei-Lun, Cao, Troy, Culp, Stacey, Napoléon, Bertrand, El-Dika, Samer, Machicado, Jorge D., Pannala, Rahul, Mok, Shaffer, Luthra, Anjuli K., Akshintala, Venkata S., Muniraj, Thiruvengadam, and Krishna, Somashekar G.
- Subjects
- *
PANCREATIC cysts , *ENDOSCOPIC ultrasonography , *BENIGN tumors , *TUMORS , *ARTIFICIAL intelligence , *MACHINE learning , *SONICATION - Abstract
Despite the increasing rate of detection of incidental pancreatic cystic lesions (PCLs), current standard-of-care methods for their diagnosis and risk stratification remain inadequate. Intraductal papillary mucinous neoplasms (IPMNs) are the most prevalent PCLs. The existing modalities, including endoscopic ultrasound and cyst fluid analysis, only achieve accuracy rates of 65–75% in identifying carcinoma or high-grade dysplasia in IPMNs. Furthermore, surgical resection of PCLs reveals that up to half exhibit only low-grade dysplastic changes or benign neoplasms. To reduce unnecessary and high-risk pancreatic surgeries, more precise diagnostic techniques are necessary. A promising approach involves integrating existing data, such as clinical features, cyst morphology, and data from cyst fluid analysis, with confocal endomicroscopy and radiomics to enhance the prediction of advanced neoplasms in PCLs. Artificial intelligence and machine learning modalities can play a crucial role in achieving this goal. In this review, we explore current and future techniques to leverage these advanced technologies to improve diagnostic accuracy in the context of PCLs. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
4. Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization
- Author
-
Chen, Junan, Monica, Josephine, Chao, Wei-Lun, and Campbell, Mark
- Subjects
FOS: Computer and information sciences ,Computer Science - Robotics ,Robotics (cs.RO) - Abstract
The uncertainty quantification of prediction models (e.g., neural networks) is crucial for their adoption in many robotics applications. This is arguably as important as making accurate predictions, especially for safety-critical applications such as self-driving cars. This paper proposes our approach to uncertainty quantification in the context of visual localization for autonomous driving, where we predict locations from images. Our proposed framework estimates probabilistic uncertainty by creating a sensor error model that maps an internal output of the prediction model to the uncertainty. The sensor error model is created using multiple image databases of visual localization, each with ground-truth location. We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting, weather (sunny, snowy, night), and alignment errors between databases. We analyze both the predicted uncertainty and its incorporation into a Kalman-based localization filter. Our results show that prediction error variations increase with poor weather and lighting condition, leading to greater uncertainty and outliers, which can be predicted by our proposed uncertainty model. Additionally, our probabilistic error model enables the filter to remove ad hoc sensor gating, as the uncertainty automatically adjusts the model to the input data, Accepted by ICRA2023
- Published
- 2023
5. Federated Learning of Shareable Bases for Personalization-Friendly Image Classification
- Author
-
Chen, Hong-You, Zhong, Jike, Zhang, Mingda, Jia, Xuhui, Qi, Hang, Gong, Boqing, Chao, Wei-Lun, and Zhang, Li
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Personalized federated learning (PFL) aims to harness the collective wisdom of clients' data to build customized models tailored to individual clients' data distributions. Existing works offer personalization primarily to clients who participate in the FL process, making it hard to encompass new clients who were absent or newly show up. In this paper, we propose FedBasis, a novel PFL framework to tackle such a deficiency. FedBasis learns a set of few, shareable ``basis'' models, which can be linearly combined to form personalized models for clients. Specifically for a new client, only a small set of combination coefficients, not the models, needs to be learned. This notion makes FedBasis more parameter-efficient, robust, and accurate compared to other competitive PFL baselines, especially in the low data regime, without increasing the inference cost. To demonstrate its applicability, we also present a more practical PFL testbed for image classification, featuring larger data discrepancies across clients in both the image and label spaces as well as more faithful training and test splits., Preprint
- Published
- 2023
6. Unified Out-Of-Distribution Detection: A Model-Specific Perspective
- Author
-
Averly, Reza and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Machine Learning (cs.LG) - Abstract
Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the scenario where OOD examples come from semantic shift (e.g., unseen categories), ignoring other possible causes (e.g., covariate shift). In this paper, we present a novel, unifying framework to study OOD detection in a broader scope. Instead of detecting OOD examples from a particular cause, we propose to detect examples that a deployed machine learning model (e.g., an image classifier) is unable to predict correctly. That is, whether a test example should be detected and rejected or not is ``model-specific''. We show that this framework unifies the detection of OOD examples caused by semantic shift and covariate shift, and closely addresses the concern of applying a machine learning model to uncontrolled environments. We provide an extensive analysis that involves a variety of models (e.g., different architectures and training strategies), sources of OOD examples, and OOD detection approaches, and reveal several insights into improving and understanding OOD detection in uncontrolled environments.
- Published
- 2023
7. Facial expression recognition based on improved local binary pattern and class-regularized locality preserving projection
- Author
-
Chao, Wei-Lun, Ding, Jian-Jiun, and Liu, Jun-Zuo
- Published
- 2015
- Full Text
- View/download PDF
8. Visual Analytics on Network Forgetting for Task‐Incremental Learning.
- Author
-
Li, Ziwei, Xu, Jiayi, Chao, Wei‐Lun, and Shen, Han‐Wei
- Subjects
VISUAL analytics ,MACHINE learning ,RIGHT to be forgotten ,INTELLIGENT agents ,TASK performance ,MEMORIZATION - Abstract
Task‐incremental learning (Task‐IL) aims to enable an intelligent agent to continuously accumulate knowledge from new learning tasks without catastrophically forgetting what it has learned in the past. It has drawn increasing attention in recent years, with many algorithms being proposed to mitigate neural network forgetting. However, none of the existing strategies is able to completely eliminate the issues. Moreover, explaining and fully understanding what knowledge and how it is being forgotten during the incremental learning process still remains under‐explored. In this paper, we propose KnowledgeDrift, a visual analytics framework, to interpret the network forgetting with three objectives: (1) to identify when the network fails to memorize the past knowledge, (2) to visualize what information has been forgotten, and (3) to diagnose how knowledge attained in the new model interferes with the one learned in the past. Our analytical framework first identifies the occurrence of forgetting by tracking the task performance under the incremental learning process and then provides in‐depth inspections of drifted information via various levels of data granularity. KnowledgeDrift allows analysts and model developers to enhance their understanding of network forgetting and compare the performance of different incremental learning algorithms. Three case studies are conducted in the paper to further provide insights and guidance for users to effectively diagnose catastrophic forgetting over time. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
9. PreSTU: Pre-Training for Scene-Text Understanding
- Author
-
Kil, Jihyung, Changpinyo, Soravit, Chen, Xi, Hu, Hexiang, Goodman, Sebastian, Chao, Wei-Lun, and Soricut, Radu
- Subjects
FOS: Computer and information sciences ,Computer Science - Computation and Language ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Computation and Language (cs.CL) - Abstract
The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability as their training objective. In this paper, we propose PreSTU, a novel pre-training recipe dedicated to scene-text understanding (STU). PreSTU introduces OCR-aware pre-training objectives that encourage the model to recognize text from an image and to connect what is recognized to the rest of the image content. We implement PreSTU using a simple transformer-based encoder-decoder architecture, combined with large-scale image-text datasets with scene text obtained from an off-the-shelf OCR system. We empirically demonstrate the effectiveness of this pre-training approach on four visual question answering and two image captioning benchmarks.
- Published
- 2022
10. Gradual Domain Adaptation without Indexed Intermediate Domains
- Author
-
Chen, Hong-You and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Machine Learning (cs.LG) - Abstract
The effectiveness of unsupervised domain adaptation degrades when there is a large discrepancy between the source and target domains. Gradual domain adaptation (GDA) is one promising way to mitigate such an issue, by leveraging additional unlabeled data that gradually shift from the source to the target. Through sequentially adapting the model along the "indexed" intermediate domains, GDA substantially improves the overall adaptation performance. In practice, however, the extra unlabeled data may not be separated into intermediate domains and indexed properly, limiting the applicability of GDA. In this paper, we investigate how to discover the sequence of intermediate domains when it is not already available. Concretely, we propose a coarse-to-fine framework, which starts with a coarse domain discovery step via progressive domain discriminator training. This coarse domain sequence then undergoes a fine indexing step via a novel cycle-consistency loss, which encourages the next intermediate domain to preserve sufficient discriminative knowledge of the current intermediate domain. The resulting domain sequence can then be used by a GDA algorithm. On benchmark data sets of GDA, we show that our approach, which we name Intermediate DOmain Labeler (IDOL), can lead to comparable or even better adaptation performance compared to the pre-defined domain sequence, making GDA more applicable and robust to the quality of domain sequences. Codes are available at https://github.com/hongyouc/IDOL., Accepted to NeurIPS 2021
- Published
- 2022
11. On the Importance and Applicability of Pre-Training for Federated Learning
- Author
-
Chen, Hong-You, Tu, Cheng-Hao, Li, Ziwei, Shen, Han-Wei, and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Machine Learning (cs.LG) - Abstract
Pre-training is prevalent in nowadays deep learning to improve the learned model's performance. However, in the literature on federated learning (FL), neural networks are mostly initialized with random weights. These attract our interest in conducting a systematic study to explore pre-training for FL. Across multiple visual recognition benchmarks, we found that pre-training can not only improve FL, but also close its accuracy gap to the counterpart centralized learning, especially in the challenging cases of non-IID clients' data. To make our findings applicable to situations where pre-trained models are not directly available, we explore pre-training with synthetic data or even with clients' data in a decentralized manner, and found that they can already improve FL notably. Interestingly, many of the techniques we explore are complementary to each other to further boost the performance, and we view this as a critical result toward scaling up deep FL for real-world applications. We conclude our paper with an attempt to understand the effect of pre-training on FL. We found that pre-training enables the learned global models under different clients' data conditions to converge to the same loss basin, and makes global aggregation in FL more stable. Nevertheless, pre-training seems to not alleviate local model drifting, a fundamental problem in FL under non-IID data., Accepted to ICLR 2023
- Published
- 2022
12. Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma.
- Author
-
Jiang, Joanna, Chao, Wei-Lun, Culp, Stacey, and Krishna, Somashekar G.
- Subjects
- *
ADENOCARCINOMA , *PANCREATIC cysts , *ENDOSCOPIC ultrasonography , *PAPILLARY carcinoma , *ARTIFICIAL intelligence , *EARLY detection of cancer , *PANCREATIC intraepithelial neoplasia , *PRECANCEROUS conditions , *NEEDLE biopsy - Abstract
Simple Summary: Pancreatic cancer will soon become the second leading cause of cancer-related death mainly due to a lack of early diagnosis. Artificial intelligence is being applied in various aspects of diagnosing medical conditions. In this review, we summarize the current literature on the application of artificial intelligence in the diagnosis and management of premalignant lesions that would otherwise progress to pancreatic cancer. Pancreatic cancer is projected to become the second leading cause of cancer-related mortality in the United States by 2030. This is in part due to the paucity of reliable screening and diagnostic options for early detection. Amongst known pre-malignant pancreatic lesions, pancreatic intraepithelial neoplasia (PanIN) and intraductal papillary mucinous neoplasms (IPMNs) are the most prevalent. The current standard of care for the diagnosis and classification of pancreatic cystic lesions (PCLs) involves cross-sectional imaging studies and endoscopic ultrasound (EUS) and, when indicated, EUS-guided fine needle aspiration and cyst fluid analysis. However, this is suboptimal for the identification and risk stratification of PCLs, with accuracy of only 65–75% for detecting mucinous PCLs. Artificial intelligence (AI) is a promising tool that has been applied to improve accuracy in screening for solid tumors, including breast, lung, cervical, and colon cancer. More recently, it has shown promise in diagnosing pancreatic cancer by identifying high-risk populations, risk-stratifying premalignant lesions, and predicting the progression of IPMNs to adenocarcinoma. This review summarizes the available literature on artificial intelligence in the screening and prognostication of precancerous lesions in the pancreas, and streamlining the diagnosis of pancreatic cancer. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
13. Tu1440 PRE-OPERATIVE RISK STRATIFICATION OF IPMNS USING FUKUOKA GUIDELINES AND CONFOCAL ENDOMICROSCOPY IMAGING
- Author
-
Leupold, Matthew, Chen, Wei, Esnakula, Ashwini K., Frankel, Wendy, Hart, Phil A., Ramsey, Mitchell L, Culp, Stacey, Shah, Zarine K., Pawlik, Timothy M., Han, Samuel, Lee, Peter, Shah, Hamza, Burlen, Jordan, Papachristou, Georgios, Chao, Wei-Lun, and Krishna, Somashekar G.
- Published
- 2024
- Full Text
- View/download PDF
14. Mo1406 IMPROVING PRE-SURGICAL RISK STRATIFICATION THROUGH EUSCONFOCAL ENDOMICROSCOPY: INSIGHTS FROM AN INTEROBSERVER AGREEMENT STUDY AMONG PANCREATICOBILIARY PATHOLOGISTS IN THE CLASSIFICATION OF DYSPLASIA FOR IPMNS
- Author
-
Leupold, Matthew, Chen, Wei, Esnakula, Ashwini K., Frankel, Wendy, Hart, Phil A., Culp, Stacey, Han, Samuel, Lee, Peter, Shah, Hamza, Burlen, Jordan, Papachristou, Georgios, Shah, Zarine K., Cloyd, Jordan, Pawlik, Timothy M., Chao, Wei-Lun, and Krishna, Somashekar G.
- Published
- 2024
- Full Text
- View/download PDF
15. Learning with Free Object Segments for Long-Tailed Instance Segmentation
- Author
-
Zhang, Cheng, Pan, Tai-Yu, Chen, Tianle, Zhong, Jike, Fu, Wenjin, and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Computer Science - Computer Vision and Pattern Recognition - Abstract
One fundamental challenge in building an instance segmentation model for a large number of classes in complex scenes is the lack of training examples, especially for rare objects. In this paper, we explore the possibility to increase the training examples without laborious data collection and annotation. We find that an abundance of instance segments can potentially be obtained freely from object-centric images, according to two insights: (i) an object-centric image usually contains one salient object in a simple background; (ii) objects from the same class often share similar appearances or similar contrasts to the background. Motivated by these insights, we propose a simple and scalable framework FreeSeg for extracting and leveraging these "free" object foreground segments to facilitate model training in long-tailed instance segmentation. Concretely, we investigate the similarity among object-centric images of the same class to propose candidate segments of foreground instances, followed by a novel ranking of segment quality. The resulting high-quality object segments can then be used to augment the existing long-tailed datasets, e.g., by copying and pasting the segments onto the original training images. Extensive experiments show that FreeSeg yields substantial improvements on top of strong baselines and achieves state-of-the-art accuracy for segmenting rare object categories., Accepted to ECCV 2022
- Published
- 2022
16. Sequential Joint Shape and Pose Estimation of Vehicles with Application to Automatic Amodal Segmentation Labeling
- Author
-
Monica, Josephine, Chao, Wei-Lun, and Campbell, Mark
- Subjects
FOS: Computer and information sciences ,Computer Science - Robotics ,Robotics (cs.RO) - Abstract
Shape and pose estimation is a critical perception problem for a self-driving car to fully understand its surrounding environment. One fundamental challenge in solving this problem is the incomplete sensor signal (e.g., LiDAR scans), especially for faraway or occluded objects. In this paper, we propose a novel algorithm to address this challenge, which explicitly leverages the sensor signal captured over consecutive time: the consecutive signals can provide more information about an object, including different viewpoints and its motion. By encoding the consecutive signals via a recurrent neural network, not only our algorithm improves the shape and pose estimates, but also produces a labeling tool that can benefit other tasks in autonomous driving research. Specifically, building upon our algorithm, we propose a novel pipeline to automatically annotate high-quality labels for amodal segmentation on images, which are hard and laborious to annotate manually. Our code and data will be made publicly available., Accepted to International Conference on Robotics and Automation (ICRA) 2022
- Published
- 2021
17. Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering
- Author
-
Kil, Jihyung, Zhang, Cheng, Xuan, Dong, and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Science - Computation and Language ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Computation and Language (cs.CL) - Abstract
Visual question answering (VQA) is challenging not only because the model has to handle multi-modal information, but also because it is just so hard to collect sufficient training examples -- there are too many questions one can ask about an image. As a result, a VQA model trained solely on human-annotated examples could easily over-fit specific question styles or image contents that are being asked, leaving the model largely ignorant about the sheer diversity of questions. Existing methods address this issue primarily by introducing an auxiliary task such as visual grounding, cycle consistency, or debiasing. In this paper, we take a drastically different approach. We found that many of the "unknowns" to the learned VQA model are indeed "known" in the dataset implicitly. For instance, questions asking about the same object in different images are likely paraphrases; the number of detected or annotated objects in an image already provides the answer to the "how many" question, even if the question has not been annotated for that image. Building upon these insights, we present a simple data augmentation pipeline SimpleAug to turn this "known" knowledge into training examples for VQA. We show that these augmented examples can notably improve the learned VQA models' performance, not only on the VQA-CP dataset with language prior shifts but also on the VQA v2 dataset without such shifts. Our method further opens up the door to leverage weakly-labeled or unlabeled images in a principled way to enhance VQA models. Our code and data are publicly available at https://github.com/heendung/simpleAUG., Accepted to EMNLP 2021
- Published
- 2021
18. On Bridging Generic and Personalized Federated Learning for Image Classification
- Author
-
Chen, Hong-You and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Machine Learning (cs.LG) - Abstract
Federated learning is promising for its capability to collaboratively train models with multiple clients without accessing their data, but vulnerable when clients' data distributions diverge from each other. This divergence further leads to a dilemma: "Should we prioritize the learned model's generic performance (for future use at the server) or its personalized performance (for each client)?" These two, seemingly competing goals have divided the community to focus on one or the other, yet in this paper we show that it is possible to approach both at the same time. Concretely, we propose a novel federated learning framework that explicitly decouples a model's dual duties with two prediction tasks. On the one hand, we introduce a family of losses that are robust to non-identical class distributions, enabling clients to train a generic predictor with a consistent objective across them. On the other hand, we formulate the personalized predictor as a lightweight adaptive module that is learned to minimize each client's empirical risk on top of the generic predictor. With this two-loss, two-predictor framework which we name Federated Robust Decoupling (Fed-RoD), the learned model can simultaneously achieve state-of-the-art generic and personalized performance, essentially bridging the two tasks., Accepted to International Conference on Learning Representations 2022 (ICLR 2022)
- Published
- 2021
19. A Comparison of Machine Learning Methods and Conventional Logistic Regression for the Prediction of In-Hospital Mortality in Acute Biliary Pancreatitis.
- Author
-
Luthra, Anjuli K., Porter, Kyle, Hinton, Alice, Chao, Wei-Lun, Papachristou, Georgios I., Conwell, Darwin L., and Krishna, Somashekar G.
- Published
- 2022
- Full Text
- View/download PDF
20. Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans.
- Author
-
Wu, Tai-Hsien, Lian, Chunfeng, Lee, Sanghee, Pastewait, Matthew, Piers, Christian, Liu, Jie, Wang, Fan, Wang, Li, Chiu, Chiung-Ying, Wang, Wenchi, Jackson, Christina, Chao, Wei-Lun, Shen, Dinggang, and Ko, Ching-Chang
- Subjects
DEEP learning ,TEETH ,CORRECTIVE orthodontics ,ORTHODONTISTS - Abstract
Accurately segmenting teeth and identifying the corresponding anatomical landmarks on dental mesh models are essential in computer-aided orthodontic treatment. Manually performing these two tasks is time-consuming, tedious, and, more importantly, highly dependent on orthodontists’ experiences due to the abnormality and large-scale variance of patients’ teeth. Some machine learning-based methods have been designed and applied in the orthodontic field to automatically segment dental meshes (e.g., intraoral scans). In contrast, the number of studies on tooth landmark localization is still limited. This paper proposes a two-stage framework based on mesh deep learning (called TS-MDL) for joint tooth labeling and landmark identification on raw intraoral scans. Our TS-MDL first adopts an end-to-end iMeshSegNet method (i.e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan. Guided by the segmentation outputs, our TS-MDL further selects each tooth’s region of interest (ROI) on the original mesh to construct a light-weight variant of the pioneering PointNet (i.e., PointNet-Reg) for regressing the corresponding landmark heatmaps. Our TS-MDL was evaluated on a real-clinical dataset, showing promising segmentation and localization performance. Specifically, iMeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at ${0.964}\pm {0.054}$ , significantly outperforming the original MeshSegNet. In the second stage, PointNet-Reg achieved a mean absolute error (MAE) of ${0}.{597}\pm {0}.{761} \, mm$ in distances between the prediction and ground truth for 66 landmarks, which is superior compared with other networks for landmark detection. All these results suggest the potential usage of our TS-MDL in orthodontics. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
21. ARTIFICIAL INTELLIGENCE-ASSISTED AUTOMATED PREDICTION OF ADVANCED NEOPLASIA IN IPMNS: A FUNCTIONAL MODEL.
- Author
-
Li, Ziwei, Park, Erica, Chao, Wei-Lun, Culp, Stacey, Hart, Phil, Chen, Wei, Jones, Daniel, Shah, Zarine, Pawlik, Timothy, and Krishna, Somashekar
- Published
- 2024
- Full Text
- View/download PDF
22. MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
- Author
-
Zhang, Cheng, Pan, Tai-Yu, Li, Yandong, Hu, Hexiang, Xuan, Dong, Changpinyo, Soravit, Gong, Boqing, and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Many objects do not appear frequently enough in complex scenes (e.g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e.g., in product images). Yet, these object-centric images are not effectively leveraged for improving object detection in scene-centric images. In this paper, we propose Mosaic of Object-centric images as Scene-centric images (MosaicOS), a simple and novel framework that is surprisingly effective at tackling the challenges of long-tailed object detection. Keys to our approach are three-fold: (i) pseudo scene-centric image construction from object-centric images for mitigating domain differences, (ii) high-quality bounding box imputation using the object-centric images' class labels, and (iii) a multi-stage training procedure. On LVIS object detection (and instance segmentation), MosaicOS leads to a massive 60% (and 23%) relative improvement in average precision for rare object categories. We also show that our framework can be compatibly used with other existing approaches to achieve even further gains. Our pre-trained models are publicly available at https://github.com/czhang0528/MosaicOS/., Accepted to ICCV 2021
- Published
- 2021
23. Wasserstein Distances for Stereo Disparity Estimation
- Author
-
Garg, Divyansh, Wang, Yan, Hariharan, Bharath, Campbell, Mark, Weinberger, Kilian Q., and Chao, Wei-Lun
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Machine Learning (cs.LG) - Abstract
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp., Accepted to NeurIPS 2020 (spotlight)
- Published
- 2020
24. Revisiting Meta-Learning as Supervised Learning
- Author
-
Chao, Wei-Lun, Ye, Han-Jia, Zhan, De-Chuan, Campbell, Mark, and Weinberger, Kilian Q.
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Statistics - Machine Learning ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Machine Learning (stat.ML) ,Machine Learning (cs.LG) - Abstract
Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to compare and evaluate. In this paper, we aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning. For example, we obtain a better understanding of generalization properties, and we can readily transfer well-understood techniques, such as model ensemble, pre-training, joint training, data augmentation, and even nearest neighbor based methods. We provide an intuitive analogy of these methods in the context of meta-learning and show that they give rise to significant improvements in model performance on few-shot learning., An extended version of the paper titled "A Meta Understanding of Meta-Learning" presented in ICML 2019 Workshop on Adaptive and Multitask Learning: Algorithms & Systems
- Published
- 2020
25. Visual Question Answering on 360{\deg} Images
- Author
-
Chou, Shih-Han, Chao, Wei-Lun, Lai, Wei-Sheng, Sun, Min, and Yang, Ming-Hsuan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
In this work, we introduce VQA 360, a novel task of visual question answering on 360 images. Unlike a normal field-of-view image, a 360 image captures the entire visual content around the optical center of a camera, demanding more sophisticated spatial understanding and reasoning. To address this problem, we collect the first VQA 360 dataset, containing around 17,000 real-world image-question-answer triplets for a variety of question types. We then study two different VQA models on VQA 360, including one conventional model that takes an equirectangular image (with intrinsic distortion) as input and one dedicated model that first projects a 360 image onto cubemaps and subsequently aggregates the information from multiple spatial resolutions. We demonstrate that the cubemap-based model with multi-level fusion and attention diffusion performs favorably against other variants and the equirectangular-based models. Nevertheless, the gap between the humans' and machines' performance reveals the need for more advanced VQA 360 algorithms. We, therefore, expect our dataset and studies to serve as the benchmark for future development in this challenging task. Dataset, code, and pre-trained models are available online., Comment: Accepted to WACV 2020
- Published
- 2020
26. 1020 ARTIFICIAL INTELLIGENCE-ASSISTED AUTOMATED EDITING AND PREDICTION OF ADVANCED NEOPLASIA IN IPMNS USING EUS-GUIDED CONFOCAL LASER ENDOMICROSCOPY: A PRELIMINARY MODEL
- Author
-
Ardeshna, Devarshi R., Tak, Divyanshu, Chao, Wei-Lun, Culp, Stacey, Cao, Troy, Turner, Ronald, Melnychuk, Jared, Nehaal, Ahmed, vishwanath, Aayush, El-Dika, Samer S., Lennon, Anne Marie, Sharma, Neil, Rojas-DeLeon, Mariajose, Pannala, Rahul, Othman, Mohamed O., and Krishna, Somashekar G.
- Published
- 2023
- Full Text
- View/download PDF
27. A New Defense Against Adversarial Images: Turning a Weakness into a Strength
- Author
-
Yu, Tao, Hu, Shengyuan, Guo, Chuan, Chao, Wei-Lun, and Weinberger, Kilian Q.
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer Science - Cryptography and Security ,Statistics - Machine Learning ,Machine Learning (stat.ML) ,Cryptography and Security (cs.CR) ,Machine Learning (cs.LG) - Abstract
Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images. While many techniques for detecting these attacks have been proposed, they are easily bypassed when the adversary has full knowledge of the detection mechanism and adapts the attack strategy accordingly. In this paper, we adopt a novel perspective and regard the omnipresence of adversarial perturbations as a strength rather than a weakness. We postulate that if an image has been tampered with, these adversarial directions either become harder to find with gradient methods or have substantially higher density than for natural images. We develop a practical test for this signature characteristic to successfully detect adversarial attacks, achieving unprecedented accuracy under the white-box setting where the adversary is given full knowledge of our detection mechanism., NeurIPS 2019, 14 pages
- Published
- 2019
28. Machine learning from clinical data sets of a contemporary decision for orthodontic tooth extraction.
- Author
-
Etemad, Lily, Wu, Tai‐Hsien, Heiner, Parker, Liu, Jie, Lee, Sanghee, Chao, Wei‐Lun, Zaytoun, Mary Lanier, Guez, Camille, Lin, Feng‐Chang, Jackson, Christina Bonebreak, and Ko, Ching‐Chang
- Abstract
Objective: To examine the robustness of the published machine learning models in the prediction of extraction vs non‐extraction for a diverse US sample population seen by multiple providers. Setting and Sample Population: Diverse group of 838 patients (208 extraction, 630 non‐extraction) were consecutively enrolled. Materials and Methods: Two sets of input features (117 and 22) including clinical and cephalometric variables were identified based on previous studies. Random forest (RF) and multilayer perception (MLP) models were trained using these feature sets on the sample population and evaluated using measures including accuracy (ACC) and balanced accuracy (BA). A technique to identify incongruent data was used to explore underlying characteristics of the data set and split all samples into 2 groups (G1 and G2) for further model training. Results: Performance of the models (75%‐79% ACC and 72%‐76% BA) on the total sample population was lower than in previous research. Models were retrained and evaluated using G1 and G2 separately, and individual group MLP models yielded improved accuracy for G1 (96% ACC and 94% BA) and G2 (88% ACC and 85% BA). RF feature ranking showed differences between top features for G1 (maxillary crowding, mandibular crowding and L1‐NB) and G2 (age, mandibular crowding and lower lip to E‐plane). Conclusions: An incongruent data pattern exists in a consecutively enrolled patient population. Future work with incongruent data segregation and advanced artificial intelligence algorithms is needed to improve the generalization ability to make it ready to support clinical decision‐making. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
29. An Empirical Study on Leveraging Scene Graphs for Visual Question Answering
- Author
-
Zhang, Cheng, Chao, Wei-Lun, and Xuan, Dong
- Subjects
FOS: Computer and information sciences ,Computer Science - Computation and Language ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Computation and Language (cs.CL) - Abstract
Visual question answering (Visual QA) has attracted significant attention these years. While a variety of algorithms have been proposed, most of them are built upon different combinations of image and language features as well as multi-modal attention and fusion. In this paper, we investigate an alternative approach inspired by conventional QA systems that operate on knowledge graphs. Specifically, we investigate the use of scene graphs derived from images for Visual QA: an image is abstractly represented by a graph with nodes corresponding to object entities and edges to object relationships. We adapt the recently proposed graph network (GN) to encode the scene graph and perform structured reasoning according to the input question. Our empirical studies demonstrate that scene graphs can already capture essential information of images and graph networks have the potential to outperform state-of-the-art Visual QA algorithms but with a much cleaner architecture. By analyzing the features generated by GNs we can further interpret the reasoning process, suggesting a promising direction towards explainable Visual QA., Accepted as oral presentation at BMVC 2019
- Published
- 2019
30. Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
- Author
-
You, Yurong, Wang, Yan, Chao, Wei-Lun, Garg, Divyansh, Pleiss, Geoff, Hariharan, Bharath, Campbell, Mark, and Weinberger, Kilian Q.
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Detecting objects such as cars and pedestrians in 3D plays an indispensable role in autonomous driving. Existing approaches largely rely on expensive LiDAR sensors for accurate depth information. While recently pseudo-LiDAR has been introduced as a promising alternative, at a much lower cost based solely on stereo images, there is still a notable performance gap. In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation. Concretely, we adapt the stereo network architecture and loss function to be more aligned with accurate depth estimation of faraway objects --- currently the primary weakness of pseudo-LiDAR. Further, we explore the idea to leverage cheaper but extremely sparse LiDAR sensors, which alone provide insufficient information for 3D detection, to de-bias our depth estimation. We propose a depth-propagation algorithm, guided by the initial depth estimates, to diffuse these few exact measurements across the entire depth map. We show on the KITTI object detection benchmark that our combined approach yields substantial improvements in depth estimation and stereo-based 3D object detection --- outperforming the previous state-of-the-art detection accuracy for faraway objects by 40%. Our code is available at https://github.com/mileyan/Pseudo_Lidar_V2., Accepted to International Conference on Learning Representations (ICLR) 2020
- Published
- 2019
31. 266 COMPUTER-AIDED DETECTION OF ADVANCED NEOPLASIA IN INTRADUCTAL PAPILLARY MUCINOUS NEOPLASMS USING CONFOCAL LASER ENDOMICROSCOPY
- Author
-
Krishna, Somashekar G., Chao, Wei-Lun, poland, sarah, Alexander, Victoria, Maloof, Tassiana, Dubay, Kelly, Ueltschi, Olivia, Middendorf, Dana M., Jajeh, Muhammed O., Vishwanath, Aadit, Porter, Kyle, Carlyn, David, Pan, Tai-Yu, Papachristou, Georgios, Hart, Phil A., Cruz-Monserrate, Zobeida, and Conwell, Darwin L.
- Published
- 2020
- Full Text
- View/download PDF
32. Video Summarization with Long Short-term Memory
- Author
-
Zhang, Ke, Chao, Wei-Lun, Sha, Fei, and Grauman, Kristen
- Subjects
FOS: Computer and information sciences ,Computer Science - Learning ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Machine Learning (cs.LG) - Abstract
We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term Memory (LSTM), a special type of recurrent neural networks to model the variable-range dependencies entailed in the task of video summarization. Our learning models attain the state-of-the-art results on two benchmark video datasets. Detailed analysis justifies the design of the models. In particular, we show that it is crucial to take into consideration the sequential structures in videos and model them. Besides advances in modeling techniques, we introduce techniques to address the need of a large number of annotated data for training complex learning models. There, our main idea is to exploit the existence of auxiliary annotated video datasets, albeit heterogeneous in visual styles and contents. Specifically, we show domain adaptation techniques can improve summarization by reducing the discrepancies in statistical properties across those datasets., To appear in ECCV 2016
- Published
- 2016
33. Mo2052 – Application of Machine Learning and Artificial Intelligence in the Detection of Dyplasia in Intraductal Papillary Mucinous Neoplasms Using Eus-Guided Needle-Based Confocal Laser Endomicroscopy
- Author
-
Krishna, Somashekar G., Chao, Wei-Lun, Strobel, Sebastian G., Stanich, Peter P., Patel, Anand, Luthra, Anjuli, Chan, Megan Q., Blaszczak, Alecia, Lee, Dana, Porter, Kyle, Hart, Phil A., Cruz-Monserrate, Zobeida, and Conwell, Darwin L.
- Published
- 2019
- Full Text
- View/download PDF
34. Synthesized Classifiers for Zero-Shot Learning.
- Author
-
Changpinyo, Soravit, Chao, Wei-Lun, Gong, Boqing, and Sha, Fei
- Published
- 2016
- Full Text
- View/download PDF
35. Summary Transfer: Exemplar-Based Subset Selection for Video Summarization.
- Author
-
Zhang, Ke, Chao, Wei-Lun, Sha, Fei, and Grauman, Kristen
- Published
- 2016
- Full Text
- View/download PDF
36. An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild.
- Author
-
Chao, Wei-Lun, Changpinyo, Soravit, Gong, Boqing, and Sha, Fei
- Published
- 2016
- Full Text
- View/download PDF
37. Facial age estimation based on label-sensitive learning and age-specific local regression.
- Author
-
Chao, Wei-Lun, Liu, Jun-Zuo, and Ding, Jian-Jiun
- Abstract
In this paper, a new age estimation framework considering the intrinsic properties of human ages is proposed, which improves the dimensionality reduction techniques to learn the connections between facial features and aging labels. To enhance the performance of dimensionality reduction, a distance metric adjustment step is introduced in advance to achieve a suitable metric in the feature space. In addition, to further exploit the ordinal relationship of human ages, the “label-sensitive” concept is proposed, which regards the label similarity during the learning phase of distance metric and dimensionality reduction. Finally, an age-specific local regression algorithm is proposed to capture the complicated aging process for age determination. From the simulation results, the proposed framework achieves the lowest mean absolute error against the existing methods. [ABSTRACT FROM PUBLISHER]
- Published
- 2012
- Full Text
- View/download PDF
38. Muscle injury determination by image segmentation.
- Author
-
Ding, Jian-Jiun, Wang, Yu-Hsiang, Hu, Lee-Lin, Chao, Wei-Lun, and Shau, Yio-Wha
- Published
- 2011
- Full Text
- View/download PDF
39. Single-shot picosecond resolution Fourier transform holographic microscopy with large field of view using a compact soft x-ray laser.
- Author
-
Wang, Shoujun, Rockwood, Alex, Wang, Yong, Chao, Wei-Lun, Naulleau, Patrick, Song, Huanyu, Menoni, Carmen S., Marconi, Mario, and Rocca, Jorge J.
- Published
- 2021
- Full Text
- View/download PDF
40. Facial age estimation based on label-sensitive learning and age-oriented regression
- Author
-
Chao, Wei-Lun, Liu, Jun-Zuo, and Ding, Jian-Jiun
- Subjects
- *
FACIAL expression , *AGE determination of human beings , *REGRESSION analysis , *ESTIMATION theory , *COMPUTER simulation , *MACHINE learning , *ERROR analysis in mathematics - Abstract
Abstract: This paper provides a new age estimation approach, which distinguishes itself with the following three contributions. First, we combine distance metric learning and dimensionality reduction to better explore the connections between facial features and age labels. Second, to exploit the intrinsic ordinal relationship among human ages and overcome the potential data imbalance problem, a label-sensitive concept and several imbalance treatments are introduced in the system training phase. Finally, an age-oriented local regression is presented to capture the complicated facial aging process for age determination. The simulation results show that our approach achieves the lowest estimation error against existing methods. [Copyright &y& Elsevier]
- Published
- 2013
- Full Text
- View/download PDF
41. High performance in risk stratification of intraductal papillary mucinous neoplasms by confocal laser endomicroscopy image analysis with convolutional neural networks (with video).
- Author
-
Machicado, Jorge D., Chao, Wei-Lun, Carlyn, David E., Pan, Tai-Yu, Poland, Sarah, Alexander, Victoria L., Maloof, Tassiana G., Dubay, Kelly, Ueltschi, Olivia, Middendorf, Dana M., Jajeh, Muhammed O., Vishwanath, Aadit B., Porter, Kyle, Hart, Phil A., Papachristou, Georgios I., Cruz-Monserrate, Zobeida, Conwell, Darwin L., and Krishna, Somashekar G.
- Abstract
EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs. A post hoc analysis of a single-center prospective study evaluating EUS-nCLE (2015-2019; INDEX study) was conducted using 15,027 video frames from 35 consecutive patients with histopathologically proven IPMNs (18 with HGD-Ca). We designed 2 CAD-convolutional neural network (CNN) algorithms: (1) a guided segmentation-based model (SBM), where the CNN-AI system was trained to detect and measure papillary epithelial thickness and darkness (indicative of cellular and nuclear stratification), and (2) a reasonably agnostic holistic-based model (HBM) where the CNN-AI system automatically extracted nCLE features for risk stratification. For the detection of HGD-Ca in IPMNs, the diagnostic performance of the CNN-CAD algorithms was compared with that of the American Gastroenterological Association (AGA) and revised Fukuoka guidelines. Compared with the guidelines, both n-CLE-guided CNN-CAD algorithms yielded higher sensitivity (HBM, 83.3%; SBM, 83.3%; AGA, 55.6%; Fukuoka, 55.6%) and accuracy (SBM, 82.9%; HBM, 85.7%; AGA, 68.6%; Fukuoka, 74.3%) for diagnosing HGD-Ca, with comparable specificity (SBM, 82.4%; HBM, 88.2%; AGA, 82.4%; Fukuoka, 94.1%). Both CNN-CAD algorithms, the guided (SBM) and agnostic (HBM) models, were comparable in risk stratifying IPMNs. EUS-nCLE-based CNN-CAD algorithms can accurately risk stratify IPMNs. Future multicenter validation studies and AI model improvements could enhance the accuracy and fully automatize the process for real-time interpretation. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
42. Application of Artificial Intelligence in the Detection and Differentiation of Colon Polyps: A Technical Review for Physicians.
- Author
-
Chao, Wei-Lun, Manickavasagan, Hanisha, and Krishna, Somashekar G.
- Subjects
- *
COLON polyps , *ARTIFICIAL intelligence , *PHYSICIANS , *VIRTUAL colonoscopy , *GASTROINTESTINAL system , *COLON cancer - Abstract
Research in computer-aided diagnosis (CAD) and the application of artificial intelligence (AI) in the endoscopic evaluation of the gastrointestinal tract is novel. Since colonoscopy and detection of polyps can decrease the risk of colon cancer, it is recommended by multiple national and international societies. However, the procedure of colonoscopy is performed by humans where there are significant interoperator and interpatient variations, and hence, the risk of missing detection of adenomatous polyps. Early studies involving CAD and AI for the detection and differentiation of polyps show great promise. In this appraisal, we review existing scientific aspects of AI in CAD of colon polyps and discuss the pitfalls and future directions for advancing the science. This review addresses the technical intricacies in a manner that physicians can comprehend to promote a better understanding of this novel application. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
43. Few-Shot Learning With a Strong Teacher.
- Author
-
Ye HJ, Ming L, Zhan DC, and Chao WL
- Abstract
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner (a meta-model) that can learn from few-shot examples to generate a classifier. Typically, the few-shot learner is constructed or meta-trained by sampling multiple few-shot tasks in turn and optimizing the few-shot learner's performance in generating classifiers for those tasks. The performance is measured by how well the resulting classifiers classify the test (i.e., query) examples of those tasks. In this paper, we point out two potential weaknesses of this approach. First, the sampled query examples may not provide sufficient supervision for meta-training the few-shot learner. Second, the effectiveness of meta-learning diminishes sharply with the increasing number of shots (i.e., the number of training examples per class). To resolve these issues, we propose a novel meta-training objective for the few-shot learner, which is to encourage the few-shot learner to generate classifiers that perform like strong classifiers. Concretely, we associate each sampled few-shot task with a strong classifier, which is trained with ample labeled examples. The strong classifiers can be seen as the target classifiers that we hope the few-shot learner to generate given few-shot examples, and we use the strong classifiers to supervise the few-shot learner. We present an efficient way to construct the strong classifier, making our proposed objective an easily plug-and-play term to existing meta-learning based FSL methods. We validate our approach, (Learning with A Strong Teacher for few-SHOT learning), in combinations with many representative meta-learning methods. On several benchmark datasets including miniImageNet and tieredImageNet, our approach leads to a notable improvement across a variety of tasks. More importantly, with our approach, meta-learning based FSL methods can consistently outperform non-meta-learning based methods at different numbers of shots, even in many-shot settings, greatly strengthening their applicability.
- Published
- 2024
- Full Text
- View/download PDF
44. Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions.
- Author
-
Rangwani S, Ardeshna DR, Rodgers B, Melnychuk J, Turner R, Culp S, Chao WL, and Krishna SG
- Abstract
The rate of incidentally detected pancreatic cystic lesions (PCLs) has increased over the past decade and was recently reported at 8%. These lesions pose a unique challenge, as each subtype of PCL carries a different risk of malignant transformation, ranging from 0% (pancreatic pseudocyst) to 34-68% (main duct intraductal papillary mucinous neoplasm). It is imperative to correctly risk-stratify the malignant potential of these lesions in order to provide the correct care course for the patient, ranging from monitoring to surgical intervention. Even with the multiplicity of guidelines (i.e., the American Gastroenterology Association guidelines and Fukuoka/International Consensus guidelines) and multitude of diagnostic information, risk stratification of PCLs falls short. Studies have reported that 25-64% of patients undergoing PCL resection have pancreatic cysts with no malignant potential, and up to 78% of mucin-producing cysts resected harbor no malignant potential on pathological evaluation. Clinicians are now incorporating artificial intelligence technology to aid in the management of these difficult lesions. This review article focuses on advancements in artificial intelligence within digital pathomics, radiomics, and genomics as they apply to the diagnosis and risk stratification of PCLs.
- Published
- 2022
- Full Text
- View/download PDF
45. Single-shot large field of view Fourier transform holography with a picosecond plasma-based soft X-ray laser.
- Author
-
Wang S, Rockwood A, Wang Y, Chao WL, Naulleau P, Song H, Menoni CS, Marconi M, and Rocca JJ
- Abstract
It is challenging to obtain nanoscale resolution images in a single ultrafast shot because a large number of photons, greater than 10
11 , are required in a single pulse of the illuminating source. We demonstrate single-shot high resolution Fourier transform holography over a broad 7 µm diameter field of view with ∼ 5 ps temporal resolution. The experiment used a plasma-based soft X-ray laser operating at 18.9 nm wavelength with nearly full spatial coherence and close to diffraction-limited divergence implemented utilizing a dual-plasma amplifier scheme. A Fresnel zone plate with a central aperture is used to efficiently generate the object and reference beams. Rapid numerical reconstruction by a 2D Fourier transform allows for real-time imaging. A half-pitch spatial resolution of 62 nm was obtained. This single-shot nanoscale-resolution imaging technique will allow for real-time ultrafast imaging of dynamic phenomena in compact setups.- Published
- 2020
- Full Text
- View/download PDF
46. Color constancy by chromaticity neutralization.
- Author
-
Chang FJ, Pei SC, and Chao WL
- Abstract
In this paper, a robust illuminant estimation algorithm for color constancy is proposed. Considering the drawback of the well-known max-RGB algorithm, which regards only pixels with the maximum image intensities, we explore the representative pixels from an image for illuminant estimation: The representative pixels are determined via the intensity bounds corresponding to a certain percentage value in the normalized accumulative histograms. To achieve the suitable percentage, an iterative algorithm is presented by simultaneously neutralizing the chromaticity distribution and preventing overcorrection. The experimental results on the benchmark databases provided by Simon Fraser University and Microsoft Research Cambridge, as well as several web images, demonstrate the effectiveness of our approach.
- Published
- 2012
- Full Text
- View/download PDF
47. Effects of acupuncture at Neiguan (PC 6) of the pericardial meridian on blood pressure and heart rate variability.
- Author
-
Chang S, Chao WL, Chiang MJ, Li SJ, Lu YT, Ma CM, Cheng HY, and Hsieh SH
- Subjects
- Adult, Autonomic Nervous System physiology, Electrocardiography, Humans, Male, Middle Aged, Parasympathetic Nervous System physiology, Pericardium innervation, Sympathetic Nervous System physiology, Acupuncture, Acupuncture Points, Blood Pressure physiology, Heart Rate physiology, Pericardium physiology
- Abstract
The aims of this study were to investigate (i) if and when the blood pressure would rise or fall and (ii) the associated changes of human heart rate variability (HRV) by manual stimulation of the Neiguan (PC 6) acupuncture site. In this paper, two groups of six healthy male volunteers with ranges of ages 20-56 and 20-55 and with no neurological diseases participated in this study. In order to minimize artefacts, the electrocardiogram (ECG) and radial arterial pulse pressure wave were collected with the subjects alert but eyes closed before, during, and after sham/manual acupuncture. No statistically significant changes (P > 0.05) were found in the sham acupuncture group. As for the manual acupuncture group, the needle was inserted into the PC 6 acupoint and manually stimulated about 15 to 30 seconds to achieve De Qi sensation. Needles were left in place for 30 min and then removed. Analysis of the data due to acupuncture was then compared with the baseline values. Results indicate that the blood pressures of different subject can either rise (P < 0.01) or fall (P < 0.01). To further determine the indicator for one subject who exhibited both rise and fall of blood pressures, 7 more trials were given conducted with the same protocol until statistically significant results were obtained (P < 0.01). We found that his change of blood pressure was highly correlated (p = -0.94 and -0.99 for rise and fall, respectively) with the ratio of the magnitude of pulse pressure to that of the dicrotic notch in the local radial pulse wave (P < 0.01). As to the heart rate variability (HRV) spectra, significant changes in the low frequency (LF) and very low frequency (VLF) ranges were also detected. These results indicate that the autonomic innervations of heart have been modified. However, the information on the power of LF, high frequency (HF), and LF/HF of HRV are not conclusive to statistically differentiate the sympathetic contribution from that of the parasympathetic nervous systems at present stage.
- Published
- 2008
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.