# Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition

Source: [Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition](<https://www.sota2.com/research/paper/68fa6de91e209131cea3ce3c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:56.231Z

Authors: Kazuki Omi, Jun Kimata, Toru Tamaki

Published: 2022-04-15T00:02:13.000Z

## Abstract

In this paper, we propose a multi-domain learning model for action recognition. The proposed method inserts domain-specific adapters between layers of domain-independent layers of a backbone network. Unlike a multi-head network that switches classification heads only, our model switches not only the heads, but also the adapters for facilitating to learn feature representations universal to multiple domains. Unlike prior works, the proposed method is model-agnostic and doesn't assume model structures unlike prior works. Experimental results on three popular action recognition datasets (HMDB51, UCF101, and Kinetics-400) demonstrate that the proposed method is more effective than a multi-head architecture and more efficient than separately training models for each domain.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2204.07270>)

[PDF](<https://arxiv.org/pdf/2204.07270.pdf>)