Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Studyby…
Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced databy Gecheng Chen, Zeyu Yang,…
UniPTS: A Unified Framework for Proficient Post-Training Sparsityby Jingjing Xie, Yuxin Zhang, Mingbao Lin, Zhihang…
Real Time Deep Learning Weapon Detection Techniques for Mitigating Lone Wolf Attacksby Kambhatla Akhila, Khaled…
RAGE Against the Machine: Retrieval-Augmented LLM Explanationsby Joel Rorseth, Parke Godfrey, Lukasz Golab, Divesh Srivastava,…
Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devicesby Baiyu Pan,…
Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosisby Qingpeng Kong, Ching-Hao Chiu, Dewen Zeng,…
Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deploymentby Abhinav Agarwalla, Abhay Gupta, Alexandre…
SFMViT: SlowFast Meet ViT in Chaotic Worldby Jiaying Lin, Jiajun Wen, Mengyuan Liu, Jinfu Liu,…
FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplicationby Eric Slyman, Stefan Lee,…