3 papers
cs.LG2026
Batch Loss Score for Dynamic Data Pruning
Qing Zhou, Bingxuan Zhao, Tao Yang +3
Dynamic data pruning accelerates deep learning by selectively omitting less informative samples during training. While per-sample loss is a common importance metric, obtaining it c…
cs.CV2025
Edge Approximation Text Detector
Chuang Yang, Xu Han, Tao Han +3
Pursuing efficient text shape representations helps scene text detection models focus on compact foreground regions and optimize the contour reconstruction steps to simplify the wh…
cs.CV2024
MMO-IG: Multi-Class and Multi-Scale Object Image Generation for Remote Sensing
Chuang Yang, Bingxuan Zhao, Qing Zhou +1
The rapid advancement of deep generative models (DGMs) has significantly advanced research in computer vision, providing a cost-effective alternative to acquiring vast quantities o…