Y
Yuyin Zhou
Researcher at Johns Hopkins University
Publications - 73
Citations - 4124
Yuyin Zhou is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Segmentation & Image segmentation. The author has an hindex of 22, co-authored 63 publications receiving 2442 citations. Previous affiliations of Yuyin Zhou include Stanford University & University of Oxford.
Papers
More filters
Proceedings ArticleDOI
Adversarial Examples for Semantic Segmentation and Object Detection
TL;DR: Zhang et al. as discussed by the authors proposed Dense Adversary Generation (DAG), which applies to the state-of-the-art networks for segmentation and detection, and found that the adversarial perturbations can be transferred across networks with different training data, based on different architectures, and even for different recognition tasks.
Proceedings ArticleDOI
Improving Transferability of Adversarial Examples With Input Diversity
TL;DR: DI-2FGSM as discussed by the authors improves the transferability of adversarial examples by creating diverse input patterns, instead of only using the original images to generate adversarial samples, the method applies random transformations to the input images at each iteration.
Posted Content
Improving Transferability of Adversarial Examples with Input Diversity
TL;DR: Zhang et al. as mentioned in this paper proposed to improve the transferability of adversarial examples by creating diverse input patterns, instead of only using the original images to generate adversarial samples, they apply random transformations to the input images at each iteration.
Posted Content
Adversarial Examples for Semantic Segmentation and Object Detection
TL;DR: This paper proposes a novel algorithm named Dense Adversary Generation (DAG), which applies to the state-of-the-art networks for segmentation and detection, and finds that the adversarial perturbations can be transferred across networks with different training data, based on different architectures, and even for different recognition tasks.
Proceedings ArticleDOI
Recurrent Saliency Transformation Network: Incorporating Multi-stage Visual Cues for Small Organ Segmentation
TL;DR: The key innovation is a saliency transformation module, which repeatedly converts the segmentation probability map from the previous iteration as spatial weights and applies these weights to the current iteration, making it more efficient and reliable in practice.