Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision-Language Models
Jiayu Li, Jiaxin Qi, Sheng Zhou +2
Contrastive vision-language models like CLIP exhibit remarkable zero-shot generalization. However, prompt tuning remains highly sensitive to label noise, as mislabeled samples gene…
cs.CV2025
Efficient Token Compression for Vision Transformer with Spatial Information Preserved
Junzhu Mao, Yang Shen, Jinyang Guo +2
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this…