Papers › On Evolving Attention Towards Domain Adaptation

On Evolving Attention Towards Domain Adaptation

25 Mar 2021arXiv:2103.13561archive 2025-07-28

Kekai Sheng, Ke Li, Xiawu Zheng, Jian Liang, WeiMing Dong, Feiyue Huang, Rongrong Ji, Xing Sun

Towards better unsupervised domain adaptation (UDA). Recently, researchers propose various domain-conditioned attention modules and make promising progresses. However, considering that the configuration of attention, i.e., the type and the position of attention module, affects the performance significantly, it is more generalized to optimize the attention configuration automatically to be specialized for arbitrary UDA scenario. For the first time, this paper proposes EvoADA: a novel framework to evolve the attention configuration for a given UDA task without human intervention. In particular, we propose a novel search space containing diverse attention configurations. Then, to evaluate the attention configurations and make search procedure UDA-oriented (transferability + discrimination), we apply a simple and effective evaluation strategy: 1) training the network weights on two domains with off-the-shelf domain adaptation methods; 2) evolving the attention configurations under the guide of the discriminative ability on the target domain. Experiments on various kinds of cross-domain benchmarks, i.e., Office-31, Office-Home, CUB-Paintings, and Duke-Market-1510, reveal that the proposed EvoADA consistently boosts multiple state-of-the-art domain adaptation approaches, and the optimal attention configurations help them achieve better performance.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationPartial Domain AdaptationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Office-Home EvoADA Accuracy 73.9 #13 of 29 Archive leaderboard report
Partial Domain Adaptation Office-Home EvoADA Accuracy (%) 80.2 #1 of 11 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market EvoADA mAP 84.3 #2 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke EvoADA mAP 71.4 #4 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections