2 papers
cs.CV2025
LEAD: Exploring Logit Space Evolution for Model Selection
Zixuan Hu, Xiaotong Li, Shixiang Tang +3
The remarkable success of pretrain-then-finetune paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a significant challenge i…
cs.CV2024
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Sha Guo, Zhuo Chen, Yang Zhao +3
Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding perf…