From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Yang, Xu, Qianqian, Wen, Peisong, Dai, Siran, Zhao, Xilin, Huang, Qingming
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912985270714368
author Liu, Yang
Xu, Qianqian
Wen, Peisong
Dai, Siran
Zhao, Xilin
Huang, Qingming
author_facet Liu, Yang
Xu, Qianqian
Wen, Peisong
Dai, Siran
Zhao, Xilin
Huang, Qingming
contents Recent studies have made notable progress in video representation learning by transferring image-pretrained models to video tasks, typically with complex temporal modules and video fine-tuning. However, fine-tuning heavy modules may compromise inter-video semantic separability, i.e., the essential ability to distinguish objects across videos. While reducing the tunable parameters hinders their intra-video temporal consistency, which is required for stable representations of the same object within a video. This dilemma indicates a potential trade-off between the intra-video temporal consistency and inter-video semantic separability during image-to-video transfer. To this end, we propose the Consistency-Separability Trade-off Transfer Learning (Co-Settle) framework, which applies a lightweight projection layer on top of the frozen image-pretrained encoder to adjust representation space with a temporal cycle consistency objective and a semantic separability constraint. We further provide a theoretical support showing that the optimized projection yields a better trade-off between the two properties under appropriate conditions. Experiments on eight image-pretrained models demonstrate consistent improvements across multiple levels of video tasks with only five epochs of self-supervised training. The code is available at https://github.com/yafeng19/Co-Settle.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26597
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning
Liu, Yang
Xu, Qianqian
Wen, Peisong
Dai, Siran
Zhao, Xilin
Huang, Qingming
Computer Vision and Pattern Recognition
Recent studies have made notable progress in video representation learning by transferring image-pretrained models to video tasks, typically with complex temporal modules and video fine-tuning. However, fine-tuning heavy modules may compromise inter-video semantic separability, i.e., the essential ability to distinguish objects across videos. While reducing the tunable parameters hinders their intra-video temporal consistency, which is required for stable representations of the same object within a video. This dilemma indicates a potential trade-off between the intra-video temporal consistency and inter-video semantic separability during image-to-video transfer. To this end, we propose the Consistency-Separability Trade-off Transfer Learning (Co-Settle) framework, which applies a lightweight projection layer on top of the frozen image-pretrained encoder to adjust representation space with a temporal cycle consistency objective and a semantic separability constraint. We further provide a theoretical support showing that the optimized projection yields a better trade-off between the two properties under appropriate conditions. Experiments on eight image-pretrained models demonstrate consistent improvements across multiple levels of video tasks with only five epochs of self-supervised training. The code is available at https://github.com/yafeng19/Co-Settle.
title From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.26597