Papers › Contextual Debiasing for Visual Recognition With Causal Mechanisms

Contextual Debiasing for Visual Recognition With Causal Mechanisms

1 Jan 2022CVPR 2022 1archive 2025-07-28

Ruyang Liu, Hao liu, Ge Li, Haodi Hou, TingHao Yu, Tao Yang

As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location. Although some studies have focused on tackling the problem, removing the negative effect of context is still challenging because it is difficult to obtain the representation of contextual bias. In this paper, we propose a simple but effective framework employing causal inference to mitigate contextual bias. We first present a Structural Causal Model (SCM) clarifying the causal relation among object representations, context, and predictions. Then, we develop a novel Causal Context Debiasing (CCD) Module to pursue the direct effect of an instance. Specifically, we adopt causal intervention to eliminate the effect of confounder and counterfactual reasoning to obtain a Total Direct Effect (TDE) free from the contextual bias. Note that our CCD framework is orthogonal to existing statistical models and thus can be migrated to any other backbones. Extensive experiments on several multi-label classification datasets demonstrate the superiority of our model over other state-of-the-art baselines.

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

Causal InferenceCounterfactual ReasoningMUlTI-LABEL-ClASSIFICATIONMulti-Label Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Classification MS-COCO CCD-SwinL mAP 90.3 #11 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO CCD-R101 mAP 85.3 #23 of 34 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