Beyond efficient fine-tuning: Efficient hybrid fine-tuning of CLIP models guided by explainable ViT attention
Authors:
- Hui YeHYHui Ye
- Xuri GeXGXuri Ge
- Junqi WangJWJunqi Wang
- Junchen FuJFJunchen Fu
- Xin XinXXXin Xin
- Jiao XueJXJiao Xue
- Yao ChenYCYao Chen
- Pengjie RenPengjie Ren
- Zhumin ChenZCZhumin Chen
- 20 January 2026
- journal article
- Published by Elsevier in Information Processing & Management
- Vol. 63 (4)
Abstract
No abstract availableThis publication has 12 references indexed in Scilit:
- Dual transferable knowledge interaction for source-free domain adaptationInformation Processing & Management, 2025
- ME-FAS: Multimodal Text Enhancement for Cross-Domain Face Anti-SpoofingIEEE Transactions on Information Forensics and Security, 2025
- A closer look at the explainability of Contrastive language-image pre-trainingPattern Recognition, 2025
- SGG-MVAR: Cross-Modal Retrieval With Scene Graph Generation and Multiview Attribute Relationship GuidanceIEEE Transactions on Computational Social Systems, 2025
- Adaptive CLIP for open-domain 3D model retrievalInformation Processing & Management, 2024
- CLIP-Adapter: Better Vision-Language Models with Feature AdaptersInternational Journal of Computer Vision, 2023
- From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptionsTransactions of the Association for Computational Linguistics, 2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Hierarchical Clustering SchemesPsychometrika, 1967
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951