Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation

TL;DR

This paper introduces EXTERN, a novel black-box video domain adaptation method utilizing endo- and exo-temporal regularizations, achieving state-of-the-art results without requiring source data or model parameters.

Contribution

The paper proposes a new approach for black-box video domain adaptation using temporal regularizations and mask-to-mix strategies, addressing privacy and portability issues.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Outperforms existing methods that require source data.

Effectively adapts across various cross-domain video tasks.

Abstract

To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models. Despite improvements made in model robustness, these VUDA methods require access to both source data and source model parameters for adaptation, raising serious data privacy and model portability issues. To cope with the above concerns, this paper firstly formulates Black-box Video Domain Adaptation (BVDA) as a more realistic yet challenging scenario where the source video model is provided only as a black-box predictor. While a few methods for Black-box Domain Adaptation (BDA) are proposed in image domain, these methods cannot apply to video domain since video modality has more complicated temporal features that are harder to align. To address BVDA, we propose a novel Endo and eXo-TEmporal Regularized Network (EXTERN) by applying mask-to-mix strategies and video-tailored regularizations: endo-temporal regularization and exo-temporal regularization, performed across both clip and temporal features, while distilling knowledge from the predictions obtained from the black-box predictor. Empirical results demonstrate the state-of-the-art performance of EXTERN across various cross-domain closed-set and partial-set action recognition benchmarks, which even surpassed most existing video domain adaptation methods with source data accessibility.