Search

This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS), which learns to segment objects of arbitrary classes using mere image-text pairs. Existing works turn to enhance the vanilla vision transformer by introducing explicit grouping recognition, i.e., employing several group tokens/centroids to cluster the image tokens and perform the group-text alignment. Nevertheless, these methods suffer from a granularity inconsistency regarding the usage of group tokens, which are aligned in the all-to-one v.s. one-to-one manners during the training and inference phases, respectively. We argue that this discrepancy arises from the lack of elaborate supervision for each group token. To bridge this granularity gap, this paper explores explicit supervision for the group tokens from the prototypical knowledge. To this end, this paper proposes the non-learnable prototypical regularization (NPR) where non-learnable prototypes are estimated from source features to serve as supervision and enable contrastive matching of the group tokens. This regularization encourages the group tokens to segment objects with less redundancy and capture more comprehensive semantic regions, leading to increased compactness and richness. Based on NPR, we propose the prototypical guidance segmentation network (PGSeg) that incorporates multi-modal regularization by leveraging prototypical sources from both images and texts at different levels, progressively enhancing the segmentation capability with diverse prototypical patterns. Experimental results show that our proposed method achieves state-of-the-art performance on several benchmark datasets. The source code is available at https://github.com/Ferenas/PGSeg., Comment: 14 pages, Accept in NeurIPS 2023

Fourier ptychography (FP) imaging, drawing on the idea of synthetic aperture, has been demonstrated as a potential approach for remote sub-diffraction-limited imaging. Nevertheless, the farthest imaging distance is still limited around 10 m even though there has been a significant improvement in macroscopic FP. The most severely issue in increasing the imaging distance is FoV limitation caused by far-field condition for diffraction. Here, we propose to modify the Fourier far-field condition for rough reflective objects, aiming to overcome the small FoV limitation by using a divergent beam to illuminate objects. A joint optimization of pupil function and target image is utilized to attain the aberration-free image while estimating the pupil function simultaneously. Benefiting from the optimized reconstruction algorithm which effectively expands the camera's effective aperture, we experimentally implement several FP systems suited for imaging distance of 12 m, 90 m, and 170 m with the maximum synthetic aperture of 200 mm. The maximum imaging distance and synthetic aperture are thus improved by more than one order of magnitude of the state-of-the-art works with a fourfold improvement in the resolution. Our findings demonstrate significant potential for advancing the field of macroscopic FP, propelling it into a new stage of development.

By applying the linearly implicit conservative difference scheme proposed in [D.-L. Wang, A.-G. Xiao, W. Yang. J. Comput. Phys. 2014;272:670-681], the system of repulsive space fractional coupled nonlinear Schr\"odinger equations leads to a sequence of linear systems with complex symmetric and Toeplitz-plus-diagonal structure. In this paper, we propose the diagonal and normal with Toeplitz-block splitting iteration method to solve the above linear systems. The new iteration method is proved to converge unconditionally, and the optimal iteration parameter is deducted. Naturally, this new iteration method leads to a diagonal and normal with circulant-block preconditioner which can be executed efficiently by fast algorithms. In theory, we provide sharp bounds for the eigenvalues of the discrete fractional Laplacian and its circulant approximation, and further analysis indicates that the spectral distribution of the preconditioned system matrix is tight. Numerical experiments show that the new preconditioner can significantly improve the computational efficiency of the Krylov subspace iteration methods. Moreover, the corresponding preconditioned GMRES method shows space mesh size independent and almost fractional order parameter insensitive convergence behaviors.

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic assumptions in practical scenarios, i.e., low-quality textual category names. For example, this paradigm assumes that new textual categories will be accurately and completely provided, and exist in lexicons during pre-training. However, exceptions often happen when encountering ambiguity for brief or incomplete names, new words that are not present in the pre-trained lexicons, and difficult-to-describe categories for users. To address these issues, this work proposes a novel attribute decomposition-aggregation framework, AttrSeg, inspired by human cognition in understanding new concepts. Specifically, in the decomposition stage, we decouple class names into diverse attribute descriptions to complement semantic contexts from multiple perspectives. Two attribute construction strategies are designed: using large language models for common categories, and involving manually labeling for human-invented categories. In the aggregation stage, we group diverse attributes into an integrated global description, to form a discriminative classifier that distinguishes the target object from others. One hierarchical aggregation architecture is further proposed to achieve multi-level aggregations, leveraging the meticulously designed clustering module. The final results are obtained by computing the similarity between aggregated attributes and images embeddings. To evaluate the effectiveness, we annotate three types of datasets with attribute descriptions, and conduct extensive experiments and ablation studies. The results show the superior performance of attribute decomposition-aggregation., Comment: Accepted to NeurIPS 2023

Seafloor observation network can perform all-weather, long-term, continuous, real-time, and in-situ observation of the ocean by combing various observation methods including cabled seafloor nodes, self-contained nodes, as well as mobile platforms, where reliable and long-term high-speed underwater wireless communication becomes an essential demand. Recently, underwater wireless optical communication (UWOC) has emerged as a highly promising solution and is rapidly becoming a research hotspot for meeting this requirement. In this article, we demonstrate the experiment and application of high-speed UWOC system for deep sea seafloor observation network. To the best of our knowledge this is the first long-term real-time deep-sea UWOC link with bitrate as high as 125 Mbps. Between 30 m distance and at a depth of 1650 m, two-way Ethernet UWOC links are realized with 125 Mbps direction-adjustable green light link and 6.25 Mbps non-line-of-sight (NLOS) blue light link. High quality video transmission of 8K 30 FPS and 4K 120 FPS are realized through high-speed 125 Mbps green light link, with 100% peak signal-to-noise ratio (PSNR) agreement, showing the capability of transmitting high-quality videos lossless. The 30-day long-term measurement results show that the BER performance of both 125 Mbps and 6.25 Mbps links is lower than 10-5, proving the stability and reliability of this UWOC system at depth of 1650 m. The maximum transmission distance for the green and blue light links are estimated to be 117.7 and 128.3 m with considering the geometry loss, which can be extended to 231.6 and 337.5 m without geometry loss. As the first long-term and real-time UWOC system in deep sea, we believe this demonstration can provide valuable experience for further UWOC studies and converged ocean observation networking with cabled and cable-less observation platforms.

This paper studies a new problem, \emph{active learning with partial labels} (ALPL). In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process. To address ALPL, we first build an intuitive baseline that can be seamlessly incorporated into existing AL frameworks. Though effective, this baseline is still susceptible to the \emph{overfitting}, and falls short of the representative partial-label-based samples during the query process. Drawing inspiration from human inference in cognitive science, where accurate inferences can be explicitly derived from \emph{counter-examples} (CEs), our objective is to leverage this human-like learning pattern to tackle the \emph{overfitting} while enhancing the process of selecting representative samples in ALPL. Specifically, we construct CEs by reversing the partial labels for each instance, and then we propose a simple but effective WorseNet to directly learn from this complementary pattern. By leveraging the distribution gap between WorseNet and the predictor, this adversarial evaluation manner could enhance both the performance of the predictor itself and the sample selection process, allowing the predictor to capture more accurate patterns in the data. Experimental results on five real-world datasets and four benchmark datasets show that our proposed method achieves comprehensive improvements over ten representative AL frameworks, highlighting the superiority of WorseNet. The source code will be available at \url{https://github.com/Ferenas/APLL}., Comment: 29 pages, Under review

In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either providing several support demonstrations from the visual aspect or characterizing the informative clues from the textual aspect (e.g., the class names). Nevertheless, both two lines neglect the complementary intrinsic of low-level visual and high-level language information, while the explorations that consider visual and textual modalities as a whole to promote predictions are still limited. To close this gap, we propose to encompass textual and visual clues as multi-modal prototypes to allow more comprehensive support for open-world semantic segmentation, and build a novel prototype-based segmentation framework to realize this promise. To be specific, unlike the straightforward combination of bi-modal clues, we decompose the high-level language information as multi-aspect prototypes and aggregate the low-level visual information as more semantic prototypes, on basis of which, a fine-grained complementary fusion makes the multi-modal prototypes more powerful and accurate to promote the prediction. Based on an elastic mask prediction module that permits any number and form of prototype inputs, we are able to solve the zero-shot, few-shot and generalized counterpart tasks in one architecture. Extensive experiments on both PASCAL-$5^i$ and COCO-$20^i$ datasets show the consistent superiority of the proposed method compared with the previous state-of-the-art approaches, and a range of ablation studies thoroughly dissects each component in our framework both quantitatively and qualitatively that verify their effectiveness., Comment: accepted in IJCV

Meta-devices have gained significant attention and have been widely utilized in optical systems for focusing and imaging, owing to their lightweight, high-integration, and exceptional-flexibility capabilities. However, based on the assumption of local phase approximation, traditional design method neglect the local lattice coupling effect between adjacent meta-atoms, thus harming the practical performance of meta-devices. Using physics-driven or data-driven optimization algorithms can effectively solve the aforementioned problems. Nevertheless, both of the methods either involve considerable time costs or require a substantial amount of data sets. Here, we propose a physics-data-driven approach based "intelligent optimizer" that enables us to adaptively modify the sizes of the studied meta-atom according to the sizes of its surrounding ones. Such a scheme allows to mitigate the undesired local lattice coupling effect, and the proposed network model works well on thousands of datasets with a validation loss of 3*10-3. Experimental results show that the 1-mm-diameter metalens designed with the "intelligent optimizer" possesses a relative focusing efficiency of 93.4% (as compared to ideal focusing) and a Strehl ratio of 0.94. In contrast to the previous inverse design method, our method significantly boosts designing efficiency with five orders of magnitude reduction in time. Our design approach may sets a new paradigm for devising large-scale meta-devices., Comment: manuscripts:19 pages, 4 figures; Supplementary Information: 11 pages, 12 figures

Postoperative complications pose a significant challenge in the healthcare industry, resulting in elevated healthcare expenses and prolonged hospital stays, and in rare instances, patient mortality. To improve patient outcomes and reduce healthcare costs, healthcare providers rely on various perioperative risk scores to guide clinical decisions and prioritize care. In recent years, machine learning techniques have shown promise in predicting postoperative complications and fatality, with deep learning models achieving remarkable success in healthcare applications. However, research on the application of deep learning models to intra-operative anesthesia management data is limited. In this paper, we evaluate the performance of transformer-based models in predicting postoperative acute renal failure, postoperative pulmonary complications, and postoperative in-hospital mortality. We compare our method's performance with state-of-the-art tabular data prediction models, including gradient boosting trees and sequential attention models, on a clinical dataset. Our results demonstrate that transformer-based models can achieve superior performance in predicting postoperative complications and outperform traditional machine learning models. This work highlights the potential of deep learning techniques, specifically transformer-based models, in revolutionizing the healthcare industry's approach to postoperative care.

Single-frame infrared small target (SIRST) detection aims at separating small targets from clutter backgrounds on infrared images. Recently, deep learning based methods have achieved promising performance on SIRST detection, but at the cost of a large amount of training data with expensive pixel-level annotations. To reduce the annotation burden, we propose the first method to achieve SIRST detection with single-point supervision. The core idea of this work is to recover the per-pixel mask of each target from the given single point label by using clustering approaches, which looks simple but is indeed challenging since targets are always insalient and accompanied with background clutters. To handle this issue, we introduce randomness to the clustering process by adding noise to the input images, and then obtain much more reliable pseudo masks by averaging the clustered results. Thanks to this "Monte Carlo" clustering approach, our method can accurately recover pseudo masks and thus turn arbitrary fully supervised SIRST detection networks into weakly supervised ones with only single point annotation. Experiments on four datasets demonstrate that our method can be applied to existing SIRST detection networks to achieve comparable performance with their fully supervised counterparts, which reveals that single-point supervision is strong enough for SIRST detection. Our code will be available at: https://github.com/YeRen123455/SIRST-Single-Point-Supervision.

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this paper, we propose to exploit such knowledgeable diffusion models for mainstream discriminative tasks, i.e., unsupervised object discovery: saliency segmentation and object localization. However, the challenges exist as there is one structural difference between generative and discriminative models, which limits the direct use. Besides, the lack of explicitly labeled data significantly limits performance in unsupervised settings. To tackle these issues, we introduce DiffusionSeg, one novel synthesis-exploitation framework containing two-stage strategies. To alleviate data insufficiency, we synthesize abundant images, and propose a novel training-free AttentionCut to obtain masks in the first synthesis stage. In the second exploitation stage, to bridge the structural gap, we use the inversion technique, to map the given image back to diffusion features. These features can be directly used by downstream architectures. Extensive experiments and ablation studies demonstrate the superiority of adapting diffusion for unsupervised object discovery.

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has long been suffering from fragmentary object regions led by Class Activation Map (CAM), which is incapable of generating fine-grained masks for semantic segmentation. To guide CAM to find more non-discriminating object patterns, this paper turns to an interesting working mechanism in agent learning named Complementary Learning System (CLS). CLS holds that the neocortex builds a sensation of general knowledge, while the hippocampus specially learns specific details, completing the learned patterns. Motivated by this simple but effective learning pattern, we propose a General-Specific Learning Mechanism (GSLM) to explicitly drive a coarse-grained CAM to a fine-grained pseudo mask. Specifically, GSLM develops a General Learning Module (GLM) and a Specific Learning Module (SLM). The GLM is trained with image-level supervision to extract coarse and general localization representations from CAM. Based on the general knowledge in the GLM, the SLM progressively exploits the specific spatial knowledge from the localization representations, expanding the CAM in an explicit way. To this end, we propose the Seed Reactivation to help SLM reactivate non-discriminating regions by setting a boundary for activation values, which successively identifies more regions of CAM. Without extra refinement processes, our method is able to achieve breakthrough improvements for CAM of over 20.0% mIoU on PASCAL VOC 2012 and 10.0% mIoU on MS COCO 2014 datasets, representing a new state-of-the-art among existing WSSS methods.