Work

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

Year: 2024

Type: conference-paper

Abstract: In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first employs self-supervised pretraining to promote discriminative feature learning on target domain videos using a teacher-guided masked distillation objective. We then perform self-training on masked target data, using the video student model and image teacher model together to generate improved pseudolabels for unlabeled target videos. Our self-training process successfully leverages the strengths of both models to achieve strong transfer performance across domains. We evaluate our approach on multiple video domain adaptation benchmarks and observe significant improvements upon previously reported results.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr52733.2024.01790

Authors: Arun Reddy, William Paul, Corban Rivera, Ketul Shah, Celso M. de Melo, Rama Chellappa

Institutions: Johns Hopkins University Applied Physics Laboratory, Johns Hopkins University, DEVCOM Army Research Laboratory, United States Army Combat Capabilities Development Command

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Army Research Office, Army Research Laboratory

Awards: G5259331294, G7452299184, G770822966