The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 행동 인식을 위한 다중 영역 학습 모델을 제안합니다. 제안하는 방법은 백본 네트워크의 도메인 독립적 계층 사이에 도메인 특정 어댑터를 삽입합니다. 분류 헤드만 전환하는 다중 헤드 네트워크와 달리 우리 모델은 헤드뿐만 아니라 여러 도메인에 보편적인 특징 표현을 쉽게 학습할 수 있도록 어댑터도 전환합니다. 이전 연구와 달리 제안된 방법은 모델에 구애받지 않으며 이전 연구와 달리 모델 구조를 가정하지 않습니다. 세 가지 인기 있는 동작 인식 데이터 세트(HMDB51, UCF101 및 Kinetics-400)에 대한 실험 결과는 제안된 방법이 다중 헤드 아키텍처보다 효과적이며 각 도메인에 대해 개별적으로 훈련하는 모델보다 효율적이라는 것을 보여줍니다.
Kazuki OMI
Nagoya Institute of Technology
Jun KIMATA
Nagoya Institute of Technology
Toru TAMAKI
Nagoya Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Kazuki OMI, Jun KIMATA, Toru TAMAKI, "Model-Agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 12, pp. 2119-2126, December 2022, doi: 10.1587/transinf.2022EDP7058.
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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7058/_p
부
@ARTICLE{e105-d_12_2119,
author={Kazuki OMI, Jun KIMATA, Toru TAMAKI, },
journal={IEICE TRANSACTIONS on Information},
title={Model-Agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition},
year={2022},
volume={E105-D},
number={12},
pages={2119-2126},
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.},
keywords={},
doi={10.1587/transinf.2022EDP7058},
ISSN={1745-1361},
month={December},}
부
TY - JOUR
TI - Model-Agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 2119
EP - 2126
AU - Kazuki OMI
AU - Jun KIMATA
AU - Toru TAMAKI
PY - 2022
DO - 10.1587/transinf.2022EDP7058
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2022
AB - 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.
ER -