3 papers
cs.CV2024
MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network
Yuming Zhang, Shouxin Zhang, Peizhe Wang +5
Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and diffi…
cs.CV2024
Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters
Yuming Zhang, Peizhe Wang, Shouxin Zhang +3
Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. Howe…
cs.CV2024
GSO-YOLO: Global Stability Optimization YOLO for Construction Site Detection
Yuming Zhang, Dongzhi Guan, Shouxin Zhang +3
Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of arti…