Fine-tuned CLIP Models are Efficient Video Learners

Authors

Hanoona Rasheed, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Muhammad Uzair Khattak, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Muhammad Maaz, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Salman Khan, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Fahad Shahbaz Khan, Mohamed Bin Zayed University of Artificial IntelligenceFollow

Document Type

Conference Proceeding

Publication Title

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Abstract

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectively transfer image-level CLIP representations to videos? In this work, we show that a simple Video Fine-tuned CLIP (ViFi-CLIP) baseline is generally sufficient to bridge the domain gap from images to videos. Our qualitative analysis illustrates that the frame-level processing from CLIP image-encoder followed by feature pooling and similarity matching with corresponding text embeddings helps in implicitly modeling the temporal cues within ViFi-CLIP. Such fine-tuning helps the model to focus on scene dynamics, moving objects and inter-object relationships. For low-data regimes where full fine-tuning is not viable, we propose a 'bridge and prompt' approach that first uses fine-tuning to bridge the domain gap and then learns prompts on language and vision side to adapt CLIP representations. We extensively evaluate this simple yet strong baseline on zero-shot, base-to-novel generalization, few-shot and fully supervised settings across five video benchmarks. Our code and pre-trained models are available at https://github.com/muzairkhattak/ViFi-CLIP.

First Page

6545

Last Page

6554

DOI

10.1109/CVPR52729.2023.00633

Publication Date

6-18-2023

Keywords

Video: Action and event understanding

Comments

Open access version from CVF

Archived, thanks to CVF

Uploaded: May 30, 2024

Recommended Citation

H. Rasheed, M. U. Khattak, M. Maaz, S. Khan and F. S. Khan, "Fine-tuned CLIP Models are Efficient Video Learners," 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 6545-6554, doi: 10.1109/CVPR52729.2023.00633.

Additional Links

https://doi.org/10.1109/CVPR52729.2023.00633