Abstract
With the emergence of pre-trained vision-language models like CLIP, how to adapt them to various downstream classification tasks has garnered significant attention in re-cent research. The adaptation strategies can be typically categorized into three paradigms: zero-shot adaptation, few-shot adaptation, and the recently-proposed training-free few-shot adaptation. Most existing approaches are tai-lored for a specific setting and can only cater to one or two of these paradigms. In this paper, we introduce a versa-tile adaptation approach that can effectively work under all three settings. Specifically, we propose the dual memory networks that comprise dynamic and static memory components. The static memory caches training data knowledge, enabling training-free few-shot adaptation, while the dynamic memory preserves historical test features online during the testing process, allowing for the exploration of additional data insights beyond the training set. This novel capability enhances model performance in the few-shot setting and enables model usability in the absence of training data. The two memory networks employ the same flexible memory interactive strategy, which can operate in a training-free mode and can be further enhanced by in-corporating learnable projection layers. Our approach is tested across 11 datasets under the three task settings. Re-markably, in the zero-shot scenario, it outperforms existing methods by over 3% and even shows superior results against methods utilizing external training data. Addition-ally, our method exhibits robust performance against nat-ural distribution shifts. Codes are available at https://github.com/YBZh/DMN.
Original language | English |
---|---|
Title of host publication | Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 |
Publisher | IEEE Computer Society |
Pages | 28718-28728 |
Number of pages | 11 |
ISBN (Electronic) | 9798350353006 |
ISBN (Print) | 9798350353013 |
DOIs | |
Publication status | Published - 21 Jun 2024 |
Event | 2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Seattle Convention Center, Seattle, United States Duration: 17 Jun 2024 → 21 Jun 2024 https://cvpr.thecvf.com/Conferences/2024 (Conference website) https://cvpr.thecvf.com/virtual/2024 (Conference website) https://cvpr.thecvf.com/virtual/2024/calendar (conference schedule) https://media.eventhosts.cc/Conferences/CVPR2024/CVPR_main_conf_2024.pdf (Conference program) https://openaccess.thecvf.com/CVPR2024 (Conference proceedings) https://ieeexplore.ieee.org/xpl/conhome/10654794/proceeding (Conference proceedings) |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
ISSN (Print) | 1063-6919 |
ISSN (Electronic) | 2575-7075 |
Conference
Conference | 2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 |
---|---|
Abbreviated title | CVPR 2024 |
Country/Territory | United States |
City | Seattle |
Period | 17/06/24 → 21/06/24 |
Internet address |
|
Scopus Subject Areas
- Software
- Computer Vision and Pattern Recognition
User-Defined Keywords
- dual memory networks
- versatile adaptation
- Vision-language models