The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation

Autor:	Zara, Giacomo, Conti, Alessandro, Roy, Subhankar, Lathuilière, Stéphane, Rota, Paolo, Ricci, Elisa
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data. The previous approaches have attempted to address SFVUDA by leveraging self-supervision (e.g., enforcing temporal consistency) derived from the target data itself. In this work, we take an orthogonal approach by exploiting "web-supervision" from Large Language-Vision Models (LLVMs), driven by the rationale that LLVMs contain a rich world prior surprisingly robust to domain-shift. We showcase the unreasonable effectiveness of integrating LLVMs for SFVUDA by devising an intuitive and parameter-efficient method, which we name Domain Adaptation with Large Language-Vision models (DALL-V), that distills the world prior and complementary source model information into a student network tailored for the target. Despite the simplicity, DALL-V achieves significant improvement over state-of-the-art SFVUDA methods. Comment: Accepted at ICCV2023, 14 pages, 7 figures, code is available at https://github.com/giaczara/dallv
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2308.09139 Zobrazit plný text záznamu View this record from Arxiv