6 papers
Multi-modal Test-time Adaptation via Adaptive Probabilistic Gaussian Calibration
Jinglin Xu, Yi Li, Chuxiong Sun +3
Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled target data during inference.…
AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning
Fei Song, Yi Li, Jiangmeng Li +4
Multi-prompt learning methods have emerged as an effective approach for facilitating the rapid adaptation of vision-language models to downstream tasks with limited resources. Exis…
Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
Fei Song, Yi Li, Rui Wang +3
Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely ba…
BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis
Shuang Cui, Jinglin Xu, Yi Li +6
Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under \textit{temporally evolving distribution shifts} common in real-worl…
Interventional Imbalanced Multi-Modal Representation Learning via -Generalization Front-Door Criterion
Yi Li, Fei Song, Changwen Zheng +3
Multi-modal methods establish comprehensive superiority over uni-modal methods. However, the imbalanced contributions of different modalities to task-dependent predictions constant…
Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
Shuang Cui, Yi Li, Jiangmeng Li +4
Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation…