3 papers
cs.CV2024
Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identification
Yue Su, Hao Li, Maoguo Gong
Visible-infrared pedestrian Re-identification (VI-ReID) aims to match pedestrian images captured by infrared cameras and visible cameras. However, VI-ReID, like other traditional c…
cs.CV2024
Triple Point Masking
Jiaming Liu, Linghe Kong, Yue Wu +5
Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point…
cs.CV2022
SBPF: Sensitiveness Based Pruning Framework For Convolutional Neural Network On Image Classification
Yiheng Lu, Maoguo Gong, Wei Zhao +2
Pruning techniques are used comprehensively to compress convolutional neural networks (CNNs) on image classification. However, the majority of pruning methods require a well pre-tr…