arXiv subjects

Dong Zhang

Publications and source records attributed to Dong Zhang.

At least 163 records · Page 9Linked to original sources

arXiv2023

Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions

Over the past few years, the rapid development of deep learning technologies for computer vision has significantly improved the performance of medical image segmentation (MedISeg). However, the diverse implementation strategies of various models have led to an extremely complex MedISeg system, resulting in a potential problem of unfair result comparisons. In this paper, we collect a series of MedISeg tricks for different model implementation phases (i.e., pre-training model, data pre-processing, data augmentation, model implementation, model inference, and result post-processing), and experimentally explore the effectiveness of these tricks on consistent baselines. With the extensive experimental results on both the representative 2D and 3D medical image datasets, we explicitly clarify the effect of these tricks. Moreover, based on the surveyed tricks, we also open-sourced a strong MedISeg repository, where each component has the advantage of plug-and-play. We believe that this milestone work not only completes a comprehensive and complementary survey of the state-of-the-art MedISeg approaches, but also offers a practical guide for addressing the future medical image processing challenges including but not limited to small dataset, class imbalance learning, multi-modality learning, and domain adaptation. The code and training weights have been released at: https://github.com/hust-linyi/seg_trick.

cs.CV↗

arXiv2023

Discrepancy-Guided Reconstruction Learning for Image Forgery Detection

In this paper, we propose a novel image forgery detection paradigm for boosting the model learning capacity on both forgery-sensitive and genuine compact visual patterns. Compared to the existing methods that only focus on the discrepant-specific patterns (\eg, noises, textures, and frequencies), our method has a greater generalization. Specifically, we first propose a Discrepancy-Guided Encoder (DisGE) to extract forgery-sensitive visual patterns. DisGE consists of two branches, where the mainstream backbone branch is used to extract general semantic features, and the accessorial discrepant external attention branch is used to extract explicit forgery cues. Besides, a Double-Head Reconstruction (DouHR) module is proposed to enhance genuine compact visual patterns in different granular spaces. Under DouHR, we further introduce a Discrepancy-Aggregation Detector (DisAD) to aggregate these genuine compact visual patterns, such that the forgery detection capability on unknown patterns can be improved. Extensive experimental results on four challenging datasets validate the effectiveness of our proposed method against state-of-the-art competitors.

cs.CV↗

arXiv2023

Rethinking Boundary Detection in Deep Learning Models for Medical Image Segmentation

Medical image segmentation is a fundamental task in the community of medical image analysis. In this paper, a novel network architecture, referred to as Convolution, Transformer, and Operator (CTO), is proposed. CTO employs a combination of Convolutional Neural Networks (CNNs), Vision Transformer (ViT), and an explicit boundary detection operator to achieve high recognition accuracy while maintaining an optimal balance between accuracy and efficiency. The proposed CTO follows the standard encoder-decoder segmentation paradigm, where the encoder network incorporates a popular CNN backbone for capturing local semantic information, and a lightweight ViT assistant for integrating long-range dependencies. To enhance the learning capacity on boundary, a boundary-guided decoder network is proposed that uses a boundary mask obtained from a dedicated boundary detection operator as explicit supervision to guide the decoding learning process. The performance of the proposed method is evaluated on six challenging medical image segmentation datasets, demonstrating that CTO achieves state-of-the-art accuracy with a competitive model complexity.

cs.CV↗

arXiv2023

Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation

Thanks to the advantages of the friendly annotations and the satisfactory performance, Weakly-Supervised Semantic Segmentation (WSSS) approaches have been extensively studied. Recently, the single-stage WSSS was awakened to alleviate problems of the expensive computational costs and the complicated training procedures in multi-stage WSSS. However, results of such an immature model suffer from problems of background incompleteness and object incompleteness. We empirically find that they are caused by the insufficiency of the global object context and the lack of the local regional contents, respectively. Under these observations, we propose a single-stage WSSS model with only the image-level class label supervisions, termed as Weakly Supervised Feature Coupling Network (WS-FCN), which can capture the multi-scale context formed from the adjacent feature grids, and encode the fine-grained spatial information from the low-level features into the high-level ones. Specifically, a flexible context aggregation module is proposed to capture the global object context in different granular spaces. Besides, a semantically consistent feature fusion module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents. Based on these two modules, WS-FCN lies in a self-supervised end-to-end training fashion. Extensive experimental results on the challenging PASCAL VOC 2012 and MS COCO 2014 demonstrate the effectiveness and efficiency of WS-FCN, which can achieve state-of-the-art results by 65.02\% and 64.22\% mIoU on PASCAL VOC 2012 val set and test set, 34.12\% mIoU on MS COCO 2014 val set, respectively. The code and weight have been released at:https://github.com/ChunyanWang1/ws-fcn.

cs.CV↗

arXiv2023

A simple iterative algorithm for maxcut

We propose a simple iterative (SI) algorithm for the maxcut problem through fully using an equivalent continuous formulation. It does not need rounding at all and has advantages that all subproblems have explicit analytic solutions, the cut values are monotonically updated and the iteration points converge to a local optima in finite steps via an appropriate subgradient selection. Numerical experiments on G-set demonstrate the performance. In particular, the ratios between the best cut values achieved by SI and those by some advanced combinatorial algorithms in [Ann. Oper. Res. 248 (2017) 365] are at least $0.986$ and can be further improved to at least $0.997$ by a preliminary attempt to break out of local optima.

math.OC↗

arXiv2023

Semantic Scene Completion with Cleaner Self

Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-posed problem as the prediction model has to "imagine" what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF). Due to the sensory imperfection of the depth camera, most existing methods based on the noisy TSDF estimated from depth values suffer from 1) incomplete volumetric predictions and 2) confused semantic labels. To this end, we use the ground-truth 3D voxels to generate a perfect visible surface, called TSDF-CAD, and then train a "cleaner" SSC model. As the model is noise-free, it is expected to focus more on the "imagination" of unseen voxels. Then, we propose to distill the intermediate "cleaner" knowledge into another model with noisy TSDF input. In particular, we use the 3D occupancy feature and the semantic relations of the "cleaner self" to supervise the counterparts of the "noisy self" to respectively address the above two incorrect predictions. Experimental results validate that our method improves the noisy counterparts with 3.1% IoU and 2.2% mIoU for measuring scene completion and SSC, and also achieves new state-of-the-art accuracy on the popular NYU dataset.

cs.CV↗

arXiv2023

A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming

Mixed-integer linear programming (MILP) is widely employed for modeling combinatorial optimization problems. In practice, similar MILP instances with only coefficient variations are routinely solved, and machine learning (ML) algorithms are capable of capturing common patterns across these MILP instances. In this work, we combine ML with optimization and propose a novel predict-and-search framework for efficiently identifying high-quality feasible solutions. Specifically, we first utilize graph neural networks to predict the marginal probability of each variable, and then search for the best feasible solution within a properly defined ball around the predicted solution. We conduct extensive experiments on public datasets, and computational results demonstrate that our proposed framework achieves 51.1% and 9.9% performance improvements to MILP solvers SCIP and Gurobi on primal gaps, respectively.

math.OC↗

arXiv2023

Learning to Reduce Information Bottleneck for Object Detection in Aerial Images

Object detection in aerial images is a fundamental research topic in the geoscience and remote sensing domain. However, the advanced approaches on this topic mainly focus on designing the elaborate backbones or head networks but ignore neck networks. In this letter, we first underline the importance of the neck network in object detection from the perspective of information bottleneck. Then, to alleviate the information deficiency problem in the current approaches, we propose a global semantic network (GSNet), which acts as a bridge from the backbone network to the head network in a bidirectional global pattern. Compared to the existing approaches, our model can capture the rich and enhanced image features with less computational costs. Besides, we further propose a feature fusion refinement module (FRM) for different levels of features, which are suffering from the problem of semantic gap in feature fusion. To demonstrate the effectiveness and efficiency of our approach, experiments are carried out on two challenging and representative aerial image datasets (i.e., DOTA and HRSC2016). Experimental results in terms of accuracy and complexity validate the superiority of our method. The code has been open-sourced at GSNet.

cs.CV↗

arXiv2023

Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan

Background: To develop an artificial intelligence system that can accurately identify acute non-traumatic intracranial hemorrhage (ICH) etiology based on non-contrast CT (NCCT) scans and investigate whether clinicians can benefit from it in a diagnostic setting. Materials and Methods: The deep learning model was developed with 1868 eligible NCCT scans with non-traumatic ICH collected between January 2011 and April 2018. We tested the model on two independent datasets (TT200 and SD 98) collected after April 2018. The model's diagnostic performance was compared with clinicians's performance. We further designed a simulated study to compare the clinicians's performance with and without the deep learning system augmentation. Results: The proposed deep learning system achieved area under the receiver operating curve of 0.986 (95% CI 0.967-1.000) on aneurysms, 0.952 (0.917-0.987) on hypertensive hemorrhage, 0.950 (0.860-1.000) on arteriovenous malformation (AVM), 0.749 (0.586-0.912) on Moyamoya disease (MMD), 0.837 (0.704-0.969) on cavernous malformation (CM), and 0.839 (0.722-0.959) on other causes in TT200 dataset. Given a 90% specificity level, the sensitivities of our model were 97.1% and 90.9% for aneurysm and AVM diagnosis, respectively. The model also shows an impressive generalizability in an independent dataset SD98. The clinicians achieve significant improvements in the sensitivity, specificity, and accuracy of diagnoses of certain hemorrhage etiologies with proposed system augmentation. Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans. It may also provide more information for clinicians for triage and further imaging examination selection.

eess.IV↗

arXiv2023

The Possible Emergence of an Attractive Inverse-Square Law from the Wave-Nature of Particles

A model of a particle in finite space is developed and the properties that the particle may possess under this model are studied. The possibility that particles attract each other due to their own wave nature is discussed. The assumption that the particles are spatially confined oscillations (SCO) in the medium is used. The relation between the SCO and the refractive index of the medium in the idealized universe is derived. Due to the plane wave constituents of SCOs, the presence of a refractive index field with a nonzero gradient causes the SCO to accelerate. The SCO locally changes the refractive index such that another SCO is accelerated towards it, and vice versa. It is concluded that the particles can attract each other due to their wave nature and an inverse-square-type acceleration emerges. The constant parameter in the inverse-square-type acceleration is used to compare with the gravitational constant $G_N$, and the possibility of non inverse-square-type behavior is preliminary discussed.

physics.gen-ph↗

arXiv2022

Protocol selection for second-order consensus against disturbance

Noticing that both the absolute and relative velocity protocols can solve the second-order consensus of multi-agent systems, this paper aims to investigate which of the above two protocols has better anti-disturbance capability, in which the anti-disturbance capability is measured by the L2 gain from the disturbance to the consensus error. More specifically, by the orthogonal transformation technique, the analytic expression of the L2 gain of the second-order multi-agent system with absolute velocity protocol is firstly derived, followed by the counterpart with relative velocity protocol. It is shown that both the L2 gains for absolute and relative velocity protocols are determined only by the minimum non-zero eigenvalue of Laplacian matrix and the tunable gains of the state and velocity. Then, we establish the graph conditions to tell which protocol has better anti-disturbance capability. Moreover, we propose a two-step scheme to improve the anti-disturbance capability of second-order multi-agent systems. Finally, simulations are given to illustrate the effectiveness of our findings.

eess.SY↗

arXiv2022

Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal

Human gesture recognition using millimeter-wave (mmWave) signals provides attractive applications including smart home and in-car interfaces. While existing works achieve promising performance under controlled settings, practical applications are still limited due to the need of intensive data collection, extra training efforts when adapting to new domains, and poor performance for real-time recognition. In this paper, we propose DI-Gesture, a domain-independent and real-time mmWave gesture recognition system. Specifically, we first derive signal variations corresponding to human gestures with spatial-temporal processing. To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework for mmWave signals based on correlations between signal patterns and gesture variations. Furthermore, a spatial-temporal gesture segmentation algorithm is employed for real-time recognition. Extensive experimental results show DI-Gesture achieves an average accuracy of 97.92\%, 99.18\%, and 98.76\% for new users, environments, and locations, respectively. We also evaluate DI-Gesture in challenging scenarios like real-time recognition and sensing at extreme angles, all of which demonstrate the superior robustness and effectiveness of our system.

cs.CV↗

arXiv2022

Centralized Feature Pyramid for Object Detection

Visual feature pyramid has shown its superiority in both effectiveness and efficiency in a wide range of applications. However, the existing methods exorbitantly concentrate on the inter-layer feature interactions but ignore the intra-layer feature regulations, which are empirically proved beneficial. Although some methods try to learn a compact intra-layer feature representation with the help of the attention mechanism or the vision transformer, they ignore the neglected corner regions that are important for dense prediction tasks. To address this problem, in this paper, we propose a Centralized Feature Pyramid (CFP) for object detection, which is based on a globally explicit centralized feature regulation. Specifically, we first propose a spatial explicit visual center scheme, where a lightweight MLP is used to capture the globally long-range dependencies and a parallel learnable visual center mechanism is used to capture the local corner regions of the input images. Based on this, we then propose a globally centralized regulation for the commonly-used feature pyramid in a top-down fashion, where the explicit visual center information obtained from the deepest intra-layer feature is used to regulate frontal shallow features. Compared to the existing feature pyramids, CFP not only has the ability to capture the global long-range dependencies, but also efficiently obtain an all-round yet discriminative feature representation. Experimental results on the challenging MS-COCO validate that our proposed CFP can achieve the consistent performance gains on the state-of-the-art YOLOv5 and YOLOX object detection baselines.

cs.CV↗

arXiv2022

Graph Reasoning Transformer for Image Parsing

Capturing the long-range dependencies has empirically proven to be effective on a wide range of computer vision tasks. The progressive advances on this topic have been made through the employment of the transformer framework with the help of the multi-head attention mechanism. However, the attention-based image patch interaction potentially suffers from problems of redundant interactions of intra-class patches and unoriented interactions of inter-class patches. In this paper, we propose a novel Graph Reasoning Transformer (GReaT) for image parsing to enable image patches to interact following a relation reasoning pattern. Specifically, the linearly embedded image patches are first projected into the graph space, where each node represents the implicit visual center for a cluster of image patches and each edge reflects the relation weight between two adjacent nodes. After that, global relation reasoning is performed on this graph accordingly. Finally, all nodes including the relation information are mapped back into the original space for subsequent processes. Compared to the conventional transformer, GReaT has higher interaction efficiency and a more purposeful interaction pattern. Experiments are carried out on the challenging Cityscapes and ADE20K datasets. Results show that GReaT achieves consistent performance gains with slight computational overheads on the state-of-the-art transformer baselines.

cs.CV↗

arXiv2022

A Novel Non-Volatile Inverter-based CiM: Continuous Sign Weight Transition and Low Power on-Chip Training

In this work, we report a novel design, one-transistor-one-inverter (1T1I), to satisfy high speed and low power on-chip training requirements. By leveraging doped HfO2 with ferroelectricity, a non-volatile inverter is successfully demonstrated, enabling desired continuous weight transition between negative and positive via the programmable threshold voltage (VTH) of ferroelectric field-effect transistors (FeFETs). Compared with commonly used designs with the similar function, 1T1I uniquely achieves pure on-chip-based weight transition at an optimized working current without relying on assistance from off-chip calculation units for signed-weight comparison, facilitating high-speed training at low power consumption. Further improvements in linearity and training speed can be obtained via a two-transistor-one-inverter (2T1I) design. Overall, focusing on energy and time efficiencies, this work provides a valuable design strategy for future FeFET-based computing-in-memory (CiM).

cond-mat.mes-hall↗

arXiv2022

Nonlinear Spectral Duality

Nonlinear eigenvalue problems for pairs of homogeneous convex functions are particular nonlinear constrained optimization problems that arise in a variety of settings, including graph mining, machine learning, and network science. By considering different notions of duality transforms from both classical and recent convex geometry theory, in this work we show that one can move from the primal to the dual nonlinear eigenvalue formulation maintaining the spectrum, the variational spectrum as well as the corresponding multiplicities unchanged. These nonlinear spectral duality properties can be used to transform the original optimization problem into various alternative and possibly more treatable dual problems. We illustrate the use of nonlinear spectral duality in a variety of example settings involving optimization problems on graphs, nonlinear Laplacians, and distances between convex bodies.

math.OC↗

arXiv2022

Rethinking the Reference-based Distinctive Image Captioning

Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC work proposes to generate distinctive captions by comparing the target image with a set of semantic-similar reference images, i.e., reference-based DIC (Ref-DIC). It aims to make the generated captions can tell apart the target and reference images. Unfortunately, reference images used by existing Ref-DIC works are easy to distinguish: these reference images only resemble the target image at scene-level and have few common objects, such that a Ref-DIC model can trivially generate distinctive captions even without considering the reference images. To ensure Ref-DIC models really perceive the unique objects (or attributes) in target images, we first propose two new Ref-DIC benchmarks. Specifically, we design a two-stage matching mechanism, which strictly controls the similarity between the target and reference images at object-/attribute- level (vs. scene-level). Secondly, to generate distinctive captions, we develop a strong Transformer-based Ref-DIC baseline, dubbed as TransDIC. It not only extracts visual features from the target image, but also encodes the differences between objects in the target and reference images. Finally, for more trustworthy benchmarking, we propose a new evaluation metric named DisCIDEr for Ref-DIC, which evaluates both the accuracy and distinctiveness of the generated captions. Experimental results demonstrate that our TransDIC can generate distinctive captions. Besides, it outperforms several state-of-the-art models on the two new benchmarks over different metrics.

cs.CV↗

arXiv2022

Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting

Background noise and scale variation are common problems that have been long recognized in crowd counting. Humans glance at a crowd image and instantly know the approximate number of human and where they are through attention the crowd regions and the congestion degree of crowd regions with a global receptive field. Hence, in this paper, we propose a novel feedback network with Region-Aware block called RANet by modeling humans Top-Down visual perception mechanism. Firstly, we introduce a feedback architecture to generate priority maps that provide prior about candidate crowd regions in input images. The prior enables the RANet pay more attention to crowd regions. Then we design Region-Aware block that could adaptively encode the contextual information into input images through global receptive field. More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity. The relevance matrix obtained would be utilized to build global relationships between pixels. Our method outperforms state-of-the-art crowd counting methods on several public datasets.

cs.CV↗