133 citations · 346 across the 21 of their papers we have counts for
21 papers
C^2GR: Coupled Comprehensive Generative Replay for a Continually Learnable Universal Segmentation Model
Wei Li, Jingyang Zhang, Guoan Wang +4
Universal segmentation models exhibit significant potential for diverse tasks involving different imaging modalities and segmentation objectives. Task-Incremental Learning provides…
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Jingyang Zhang, Jingkang Yang, Pengyun Wang +9
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods…
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection
Jingyang Zhang, Nathan Inkawhich, Randolph Linderman +3
Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training. In this work, we develop a data-driven approach which…
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation
Ran Gu, Guotai Wang, Jiangshan Lu +8
Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to d…
Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classification
Randolph Linderman, Jingyang Zhang, Nathan Inkawhich +2
Machine learning methods must be trusted to make appropriate decisions in real-world environments, even when faced with out-of-distribution (OOD) samples. Many current approaches s…
Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures
Ran Gu, Jingyang Zhang, Guotai Wang +5
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised…
Contrastive Domain Disentanglement for Generalizable Medical Image Segmentation
Ran Gu, Jiangshan Lu, Jingyang Zhang +4
Efficiently utilizing discriminative features is crucial for convolutional neural networks to achieve remarkable performance in medical image segmentation and is also important for…
Privacy Leakage of Adversarial Training Models in Federated Learning Systems
Jingyang Zhang, Yiran Chen, Hai Li
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerabl…
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments
Jingyang Zhang, Nathan Inkawhich, Randolph Linderman +2
Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification)…
SS-CADA: A Semi-Supervised Cross-Anatomy Domain Adaptation for Coronary Artery Segmentation
Jingyang Zhang, Ran Gu, Guotai Wang +2
The segmentation of coronary arteries by convolutional neural network is promising yet requires a large amount of labor-intensive manual annotations. Transferring knowledge from re…
MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
Xiangde Luo, Guotai Wang, Tao Song +6
Segmentation of organs or lesions from medical images plays an essential role in many clinical applications such as diagnosis and treatment planning. Though Convolutional Neural Ne…
Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
Nathan Inkawhich, Kevin J Liang, Jingyang Zhang +3
We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and…
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
Huanrui Yang, Jingyang Zhang, Hongliang Dong +6
Recent research finds CNN models for image classification demonstrate overlapped adversarial vulnerabilities: adversarial attacks can mislead CNN models with small perturbations, w…
Visibility-aware Multi-view Stereo Network
Jingyang Zhang, Yao Yao, Shiwei Li +2
Learning-based multi-view stereo (MVS) methods have demonstrated promising results. However, very few existing networks explicitly take the pixel-wise visibility into consideration…
Learning Stereo Matchability in Disparity Regression Networks
Jingyang Zhang, Yao Yao, Zixin Luo +4
Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are texture…
Weakly Supervised Vessel Segmentation in X-ray Angiograms by Self-Paced Learning from Noisy Labels with Suggestive Annotation
Jingyang Zhang, Guotai Wang, Hongzhi Xie +4
The segmentation of coronary arteries in X-ray angiograms by convolutional neural networks (CNNs) is promising yet limited by the requirement of precisely annotating all pixels in…
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
Yao Yao, Zixin Luo, Shiwei Li +5
While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compar…
Exploring Bit-Slice Sparsity in Deep Neural Networks for Efficient ReRAM-Based Deployment
Jingyang Zhang, Huanrui Yang, Fan Chen +2
Emerging resistive random-access memory (ReRAM) has recently been intensively investigated to accelerate the processing of deep neural networks (DNNs). Due to the in-situ computati…
Multi-Scale Time-Frequency Attention for Acoustic Event Detection
Jingyang Zhang, Wenhao Ding, Jintao Kang +1
Most attention-based methods only concentrate along the time axis, which is insufficient for Acoustic Event Detection (AED). Meanwhile, previous methods for AED rarely considered t…
Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack
Jingyang Zhang, Hsin-Pai Cheng, Chunpeng Wu +2
In recent years, deep neural networks demonstrated state-of-the-art performance in a large variety of tasks and therefore have been adopted in many applications. On the other hand,…
A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria
Yu Zhao, Zhenhui Shi, Jingyang Zhang +2
Multiple query criteria active learning (MQCAL) methods have a higher potential performance than conventional active learning methods in which only one criterion is deployed for sa…