Search

Crawler detection is always an important research topic in network security. With the development of web technology, crawlers are constantly updating and changing, and their types are becoming diverse. The diversity and dynamics of crawlers pose significant challenges for feature applicability and model robustness. Existing crawler detection methods can only detect a limited number of crawlers by predefined rules and can not cover all types of crawlers; worse, they can be completely invalidated by the emergence of new types of crawlers. In this paper, we propose a reinforcement learning based web crawler detection method for diversity and dynamics (WC3D), which is composed of a feature selector and a session classifier. The feature selector selects the appropriate feature set for different types of crawlers with deep deterministic policy gradient. The session classifier makes crawler detection and provides rewards to the feature selector. The two modules are trained jointly to optimize the feature selection and session classification processes. Extensive experiments demonstrate the existence of crawler diversity and that the proposed method is still highly robust against the new type of crawlers and achieves state-of-the-art performance even without considering the dynamics of the crawlers. [ABSTRACT FROM AUTHOR]

• We introduce the disassembling task and an unsupervised approach towards solving it. • UDOR is devised to comply with the modularity of the learned latent representation. • We also introduce two metrics for evaluating the disassembling performance. In this paper, we study a new representation-learning task, which we termed as disassembling object representations. Given an image featuring multiple objects, the goal of disassembling is to acquire a latent representation, of which each part corresponds to one category of objects. Disassembling thus finds its application in a wide domain such as image editing and few- or zero-shot learning, as it enables category-specific modularity in the learned representations. To this end, we propose an unsupervised approach to achieving disassembling, named Unsupervised Disassembling Object Representation (UDOR). UDOR follows a double auto-encoder architecture, in which a fuzzy classification and an object-removing operation are imposed. The fuzzy classification constrains each part of the latent representation to encode features of up to one object category, while the object-removing, combined with a generative adversarial network, enforces the modularity of the representations and integrity of the reconstructed image. Furthermore, we devise two metrics to respectively measure the modularity of disassembled representations and the visual integrity of reconstructed images. Experimental results demonstrate that the proposed UDOR, despite unsupervised, achieves truly encouraging results on par with those of supervised methods. [ABSTRACT FROM AUTHOR]

Image-based nondestructive textile fiber identification is a challenging computer vision problem, that is practically useful in fashion, decoration, and design. Although deep learning now outperforms humans in many scenarios such as face and object recognition, image-based fiber identification is still an open problem for deep learning given imbalanced sample and small sample size samples. In this paper, we propose the Component Unmixing Network (CU-Net) for nondestructive textile fiber identification. CU-Net learns effective representations given imbalanced sample and small sample size samples to achieve high-performance textile fiber identification. CU-Net comprises a Deep Feature Extraction Module (DFE-Module) and a Component Unmixing Module (CU-Module). Initially, mixed deep features are extracted by DFE-Module from the input textile patches. Then, CU-Module is employed to extract unmixed representations of different fibers from the mixed deep features. In CU-Module, we introduce a self-interchange and a restraining loss to reduce the mixture between representations of different fibers. Furthermore, we extend CU-Net to the proportion analysis task with very good effect. Extensive experiments demonstrate that: (1) self-interchange and the restraining loss effectively unmix different fiber representations and improve fiber identification accuracy; and (2) CU-Net achieves more accurate fiber identification than the current state-of-the-art multi-label classification methods. [ABSTRACT FROM AUTHOR]

Extracting color themes from an image is to get a color palette that consists of dominant colors of the image. In this article, we construct a color network to build the intrinsic connections of color information of pixels. By applying improved linear iterative clustering (SLIC) algorithm [1,2] , we obtain initial color themes. In the following stage, with learning from human-extract color themes, we can get the final sorted color themes result. Experimental results demonstrate that our model outperforms previous approaches in terms of the number of themes, span and accuracy. [ABSTRACT FROM AUTHOR]

We aimed to develop an explainable and reliable method to diagnose cysts and tumors of the jaw with massive panoramic radiographs of healthy peoples based on deep learning, since collecting and labeling massive lesion samples are time-consuming, and existing deep learning-based methods lack explainability. Based on the collected 872 lesion samples and 10,000 healthy samples, a two-branch network was proposed for classifying the cysts and tumors of the jaw. The two-branch network is firstly pretrained on massive panoramic radiographs of healthy peoples, then is trained for classifying the sample categories and segmenting the lesion area. Totally, 200 healthy samples and 87 lesion samples were included in the testing stage. The average accuracy, precision, sensitivity, specificity, and F1 score of classification are 88.72%, 65.81%, 66.56%, 92.66%, and 66.14%, respectively. The average accuracy, precision, sensitivity, specificity, and F1 score of classification will reach 90.66%, 85.23%, 84.27%, 93.50%, and 84.74%, if only classifying the lesion samples and healthy samples. The proposed method showed encouraging performance in the diagnosis of cysts and tumors of the jaw. The classified categories and segmented lesion areas serve as the diagnostic basis for further diagnosis, which provides a reliable tool for diagnosing jaw tumors and cysts. [ABSTRACT FROM AUTHOR]

Effective transfer learning for molecular property prediction has shown considerable strength in addressing insufficient labeled molecules. Many existing methods either disregard the quantitative relationship between source and target properties, risking negative transfer, or require intensive training on target tasks. To quantify transferability concerning task-relatedness, we propose Principal Gradient-based Measurement (PGM) for transferring molecular property prediction ability. First, we design an optimization-free scheme to calculate a principal gradient for approximating the direction of model optimization on a molecular property prediction dataset. We have analyzed the close connection between the principal gradient and model optimization through mathematical proof. PGM measures the transferability as the distance between the principal gradient obtained from the source dataset and that derived from the target dataset. Then, we perform PGM on various molecular property prediction datasets to build a quantitative transferability map for source dataset selection. Finally, we evaluate PGM on multiple combinations of transfer learning tasks across 12 benchmark molecular property prediction datasets and demonstrate that it can serve as fast and effective guidance to improve the performance of a target task. This work contributes to more efficient discovery of drugs, materials, and catalysts by offering a task-relatedness quantification prior to transfer learning and understanding the relationship between chemical properties. Transfer learning is known to enhance molecular property prediction in limited data sets, however, negative transfer due to insufficient relatedness between source and target tasks continues to be a major challenge. Here, the authors develop a principal gradient-based measurement to evaluate the quantitative transferability from the source property to the target property before applying transfer learning, significantly improving the transfer learning performance. [ABSTRACT FROM AUTHOR]

Background: Microvascular invasion (MVI) is an independent prognostic factor that is associated with early recurrence and poor survival after resection of hepatocellular carcinoma (HCC). However, the traditional pathology approach is relatively subjective, time‐consuming, and heterogeneous in the diagnosis of MVI. The aim of this study was to develop a deep‐learning model that could significantly improve the efficiency and accuracy of MVI diagnosis. Materials and Methods: We collected H&E‐stained slides from 753 patients with HCC at the First Affiliated Hospital of Zhejiang University. An external validation set with 358 patients was selected from The Cancer Genome Atlas database. The deep‐learning model was trained by simulating the method used by pathologists to diagnose MVI. Model performance was evaluated with accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve. Results: We successfully developed a MVI artificial intelligence diagnostic model (MVI‐AIDM) which achieved an accuracy of 94.25% in the independent external validation set. The MVI positive detection rate of MVI‐AIDM was significantly higher than the results of pathologists. Visualization results demonstrated the recognition of micro MVIs that were difficult to differentiate by the traditional pathology. Additionally, the model provided automatic quantification of the number of cancer cells and spatial information regarding MVI. Conclusions: We developed a deep learning diagnostic model, which performed well and improved the efficiency and accuracy of MVI diagnosis. The model provided spatial information of MVI that was essential to accurately predict HCC recurrence after surgery. [ABSTRACT FROM AUTHOR]

Deep learning (DL)-based models especially Convolutional Neural Network (CNN) models have recently achieved great success in medical image classifications. It is usually time-consuming and labor-intensive to train a practical classification model due to the requirement of large data volume. Since medical images are more difficult to acquire and label for model training, many scholars have applied transfer learning by pre-training a model on a larger dataset and then fine-tuning it on the target dataset to obtain better classification results. However, such approach, relying on individual expertise to select related datasets, is subjective and inconsistent in performance. In this paper, we propose a simple yet effective method for measuring the transferability between different datasets, and build a Dataset Map (DataMap) that can be used as a tool to find the most relevant datasets for transfer learning on target dataset. Recent studies show that the convolutional kernels in CNN models have different function roles. Therefore, we adopt the similarity between the convolution kernels to measure the transferability between datasets. Firstly, the gradient attribution is adopted to attribute the task related convolution kernels from last few convolution layers of the same pre-trained model architecture trained with different datasets. Then, the similarity between attributed convolutional kernels is calculated to denote the transferability between different datasets. Finally, we build a DataMap with 20 medical image datasets. Extensive experimental tests on 3 mainstream CNN architectures show that the proposed method can effectively measure the transferability between different datasets. With the guidance of the DataMap, the transfer learning can achieve the best performance on various training tasks, and the accuracy of the CNN classifier can be improved by 1% to 5% through pre-training. • The first DataMap used to instruct transfer learning for medical image classificaton. • Adopt the similarity between the convolution kernels to measure the transferability. • With the guidance of DataMap, transfer learning can achieve the best performance. [ABSTRACT FROM AUTHOR]

In recent years, the convolutional segmentation network has achieved remarkable performance in the computer vision area. However, training a practicable segmentation network is time- and resource-consuming. In this paper, focusing on the semantic image segmentation task, we attempt to disassemble a convolutional segmentation network into category-aware convolution kernels and achieve customizable tasks without additional training by utilizing those kernels. The core of disassembling convolutional segmentation networks is how to identify the relevant convolution kernels for a specific category. According to the encoder-decoder network architecture, the disassembling framework, named Disassembler, is devised to be composed of the forward channel-wise activation attribution and backward gradient attribution. In the forward channel-wise activation attribution process, for each image, the activation values of each feature map in the high-confidence mask area are summed into category-aware probability vectors. In the backward gradient attribution process, the positive gradients w.r.t. each feature map in the high-confidence mask area are summed into a relative coefficient vector for each category. With the cooperation of two vectors, the Disassembler can effectively disassemble category-aware convolution kernels. Extensive experiments demonstrate that the proposed Disassembler can accomplish the category-customizable task without additional training. The disassembled category-aware sub-network achieves comparable performance without any finetuning and will outperform existing state-of-the-art methods with one epoch of finetuning. [ABSTRACT FROM AUTHOR]

With the wide-spread of smartphones, mobile phone screen has become an important IO device in HCI and its quality is of great matter in interaction. Traditional defect detection process involves heavy labor cost or relies on unstable low-level features and suffers from both scale and model sensitive problems. Screen defect varies in size, shape, intensity and is hard to be described. Efficient and accurate detection system remains an urgent need in mobile phone screen manufacturing. In this paper, we propose an end-to-end screen defect detection framework. A defect detection network with merging and splitting strategies (MSDDN) to deal with multiple size and shape variations of defect image patches is firstly designed. After training, feature maps of the last layer before the output of MSDDN can be regarded as good representations of a screen image patch. These feature maps are concatenated into a unified feature vector. We then train a recurrent neural network (SCN) to decide which input screen image patch in a sequence is the most likely to contain defects, where the patches are cropped from the same image, and the feature maps are used as input. As SCN emphasizes on the comparison of image patches from one image, it is less sensitive to different screen batches. The patch with the highest probability of containing defects, or called focus area, is further processed with a sliding window to fill in the MSDDN to produce the final results. Finally, to improve the efficiency of the calculation process to fulfill the real industrial demand, we perform both filter selection and weight quantization on the weights in MSDDN under the purpose of building a low-precision version network without great loss in accuracy (MSDDN-l). Experimental results show MSDDN can better handle the defect variations than traditional models and general purpose convolutional neural networks. Meanwhile, SCN can accurately predict the focus area, and MSDDN-l can greatly improve the efficiency. [ABSTRACT FROM AUTHOR]

Vision transformers have achieved remarkable success in computer vision tasks by using multi-head self-attention modules to capture long-range dependencies within images. However, the high inference computation cost poses a new challenge. Several methods have been proposed to address this problem, mainly by slimming patches. In the inference stage, these methods classify patches into two classes, one to keep and the other to discard in multiple layers. This approach results in additional computation at every layer where patches are discarded, which hinders inference acceleration. In this study, we tackle the patch slimming problem from a different perspective by proposing a life regression module that determines the lifespan of each image patch in one go. During inference, the patch is discarded once the current layer index exceeds its life. Our proposed method avoids additional computation and parameters in multiple layers to enhance inference speed while maintaining competitive performance. Additionally, our approach 1 1 https://github.com/cjwcommuny/life-regression. requires fewer training epochs than other patch slimming methods. [ABSTRACT FROM AUTHOR]

Object detection is one of the core tasks in computer vision that serves as a crucial underpinning for numerous applications. In recent years, deep learning-based methods have achieved remarkable performance in object detection. However, the performance of small objects still remains unsatisfactory. Therefore, some specific architectures have been proposed to address this issue in certain areas, such as remote-sensing and UAV images. In this paper, we aim to design a pluggable and non-intrusive method, termed as PatchDetector, to improve the performance of small object detection, which can effectively avoid the time and resource overhead of retraining the entire network. To achieve that, we first analyze why the mainstream networks perform poorly on small objects and find out that the fundamental reason is that the features of small are superseded by the background, which leads to a significant semantic gap in multi-level layers. Then, significance analysis is conducted to find the essential features for improving the small object detection. Next, with the located significant features, we devise a pluggable patch network for extracting essential features for small objects, which is non-intrusive to the original network. Experiments on mainstream detectors, including YOLO series and Faster RCNN, show that the proposed PatchDetector achieves 0. 4 % ∼ 2. 0 % mAP on small objects while not compromising the performance of medium and large objects. • The first pluggable and non-intrusive patch for small object detection performance. • We analyze the small object poor performance and locate the essential features. • Experiments demonstrate that the PatchDetector achieves 0. 4 % ∼ 2. 0 % mAP on small object. [ABSTRACT FROM AUTHOR]

Video highlight detection (VHD) has emerged as a pressing task due to the unprecedentedly increasing amount of video data, such as those from e-commerce live-broadcasting platforms. Many approaches focus on exploiting text data, in the form of video description or time-sync comments, to facilitate the VHD task. Despite the promising results, they have largely overlooked the noises inherent in the text data and have mostly relied on isolating the feature of text and video. In this paper, we introduce a novel model to handle VHD, termed Coevolution Network (CoEvo-Net), that allows us to account for joint learning of the language and video features explicitly via a coevolution paradigm, in which features from the two data modalities progressively refine each other. This is achieved by a dedicated CoEvo-Cell that takes language and video together as inputs, extracts cross-modality, and filters the undesired parts of the input, such as words in a sentence. Furthermore, we release a large-scale dataset of e-commerce for VHD, in which each video is coupled with a sentence for description, to benchmark the sentence-based VHD approaches. Extensive experiments on the released dataset demonstrate that CoEvo-Net achieves state-of-the-art performance. Our dataset and code will be made publicly available. [ABSTRACT FROM AUTHOR]

Recently, many benchmark datasets have been found to contain noisy labels caused by unavoidable human mistakes. Many researchers propose new noise-aware loss functions to achieve robust classification performance. However, we discover that existing noise-aware loss functions cannot fully heal the damage caused by the noise. On the other hand, some methods filter out low confidence samples and train new models, whereas the filtered samples contain both noisy and hard samples that are critical for the robustness of models. Based on the above two discoveries, we devised the Noise-aware Network (NA-Net) for robust training with noisy labels. Each layer of NA-Net contains three groups of convolution kernels responsible for mix samples, clean samples, and noisy samples, termed as mix-kernels, clean-kernels, and noise-kernels, respectively. Mix-kernels are used for finding the clean samples with a newly devised noise-immune (NI) loss function; clean-kernels are targeted at learning better features without being misguided by noise; noise-kernels are trained by the remaining samples to rectify wrong labels for the next iteration. Meanwhile, for increasing the classification performance of mix-kernels, the extracted feature maps of clean-kernels without being poisoned are combined as the input of mix-kernels of the next layer. Also, the knowledge distillation strategy is adopted to distill the knowledge from clean-kernels to the noise-kernels. Extensive experiments demonstrate that the mutual promotion of three groups of kernels in NA-Net achieves state-of-the-art performance on both artificial noisy datasets and real-world datasets. • The first to clarify the influence extent of noisy and hard samples for training. • Noise-aware Network with separate groups of kernels is proposed for handling noise. • A new loss function is proposed to make the training robust to the noise. [ABSTRACT FROM AUTHOR]

In the field of weakly supervised semantic segmentation (WSSS), Class Activation Maps (CAM) are typically adopted to generate pseudo masks. Yet, we find that the crux of the unsatisfactory pseudo masks is the incomplete CAM. Specifically, as convolutional neural networks tend to be dominated by the specific regions in the high-confidence channels of feature maps during prediction, the extracted CAM contains only parts of the object. To address this issue, we propose the Disturbed CAM (DCAM), a simple yet effective method for WSSS. Following CAM, we adopt a binary cross-entropy (BCE) loss to train a multi-label classification model. Then, we disturb the feature map with retraining to enhance the high-confidence channels. In addition, a softmax cross-entropy (SCE) loss branch is employed to increase the model attention to the target classes. Once converged, we extract DCAM in the same way as in CAM. The evaluation on both PASCAL VOC and MS COCO shows that DCAM not only generates high-quality masks (6.2% and 1.4% higher than the benchmark models), but also enables more accurate activation in object regions. The code is available at https://github.com/gyyang23/DCAM. • A simple yet effective method DCAM for generating pseudo masks. • DCAM promotes more patterns to the prediction, identifying more object regions. • Extensive experiments on benchmarks datasets demonstrate the effectiveness of DCAM. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image classification. Although remarkable advancement has been made, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the unavoidable hard samples and minority class samples. Meanwhile, it is hard to understand the prediction mechanism and debug the wrong prediction. To address these issues, this paper proposes a Self-Optimizing medical image classification framework based on category-aware feature attribution, which automatically performs model diagnosis, repairing, and enhancement. On one hand, we introduce selective filter restraining to alleviate the disturbance of misclassified features for hard samples. On the other hand, we introduce sample-specific fine-tuning to promote category-wise feature learning, especially for minority classes. The Self-Optimizing framework is a versatile module for other medical image classifiers based on mainstream CNN structures. We extensively validated the proposed method on three typical yet challenging medical image classification tasks: (i) skin lesion classification from dermoscopic images in the International Skin Imaging Collaboration (ISIC) 2019 dataset, (ii) breast cancer classification from ultrasound images in Breast Ultrasound Images (BUSI) dataset, and (iii) breast tumour classification from histopathologic scans of lymph node sections in PatchCamelyon (PCam) dataset. Experimental results demonstrate that the proposed framework achieves 1% ∼ 5% performance gain for various classifiers, brings better explainability, and can be applied to incremental learning scenarios. • A framework automatically performs model diagnosis, repairing, and enhancement. • Introduce selective filter restraining to alleviate the misclassified features. • Introduce sample-specific fine-tuning to promote category-wise feature learning. • The Self-Optimizing framework is a versatile module for medical image classifiers. [ABSTRACT FROM AUTHOR]