TY - GEN
T1 - Attribute-Guided Zero-Shot CLIP in Image Classification
AU - Qiu, Guoxi
AU - Zhang, Xiangyu
AU - Xu, Yong
AU - Wang, Jinghua
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Contrastive Language-Image Pre-training (CLIP) has shown strong performance in zero-shot image classification. However, it requires large datasets and high computational costs. In this paper, we propose a transferable module that improves CLIP's zero-shot classification accuracy by integrating image-specific attributes into prompts during inference. This method enhances CLIP's performance without additional training and extends its applicability to other vision-language models (VLMs), offering an efficient solution for image classification tasks.
AB - Contrastive Language-Image Pre-training (CLIP) has shown strong performance in zero-shot image classification. However, it requires large datasets and high computational costs. In this paper, we propose a transferable module that improves CLIP's zero-shot classification accuracy by integrating image-specific attributes into prompts during inference. This method enhances CLIP's performance without additional training and extends its applicability to other vision-language models (VLMs), offering an efficient solution for image classification tasks.
KW - Attribute
KW - Contrastive Learning
KW - image classification
UR - https://www.scopus.com/pages/publications/105022630298
U2 - 10.1109/ICME59968.2025.11209250
DO - 10.1109/ICME59968.2025.11209250
M3 - 会议稿件
AN - SCOPUS:105022630298
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2025 IEEE International Conference on Multimedia and Expo
PB - IEEE Computer Society
T2 - 2025 IEEE International Conference on Multimedia and Expo, ICME 2025
Y2 - 30 June 2025 through 4 July 2025
ER -