2 papers
cs.LG2026
RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples
Chao Zhou, Shenghua He, Jiaxin Mo +2
Decision-based sparse attacks must reduce perturbation support using only the victim's predicted label. The best restoration strategy varies as support contracts: coarse removal wo…
cs.CV2026
Smooth bounding box for object detection
Chao Zhou, Shenghua He, Fengchuang Xing +2
Deep learning-based object detection models are highly dependent on the quality of annotated training data. However, large-scale datasets often contain inevitable label noise, with…