Papers › Causality Compensated Attention for Contextual Biased Visual Recognition

Causality Compensated Attention for Contextual Biased Visual Recognition

25 Feb 2023ICLR 2023 2archive 2025-07-28

Ruyang Liu, Jingjia Huang, Ge Li, Thomas H. Li

Visual attention does not always capture the essential object representation desired for robust predictions. Attention modules tend to underline not only the target object but also the common co-occurring context that the module thinks helpful in the training. The problem is rooted in the confounding effect of the context leading to incorrect causalities between objects and predictions, which is further exacerbated by visual attention. In this paper, to learn causal object features robust for contextual bias, we propose a novel attention module named Interventional Dual Attention (IDA) for visual recognition. Specifically, IDA adopts two attention layers with multiple sampling intervention, which compensates the attention against the confounder context. Note that our method is model-agnostic and thus can be implemented on various backbones. Extensive experiments show our model obtains significant improvements in classification and detection with lower computation. In particular, we achieve the state-of-the-art results in multi-label classification on MS-COCO and PASCAL-VOC.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

MUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationMulti-Label Image ClassificationObject

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Classification MS-COCO IDA-SwinL mAP 90.3 #10 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO IDA-R101 mAP 86.3 #21 of 34 Archive leaderboard report
Multi-Label Image Classification MSCOCO IDA-R101(H) mAP 84.8 #1 of 4 Archive leaderboard report
Multi-Label Image Classification MSCOCO IDA-R101(H) 576 mAP 86.3 #2 of 4 Archive leaderboard report
Multi-Label Image Classification MSCOCO IDA-SwinL(H) 384 mAP 90.3 #3 of 4 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