Papers › Consistency Learning via Decoding Path Augmentation for Transformers in Human Object...
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection
Jihwan Park, Seungjun Lee, Hwan Heo, Hyeong Kyu Choi, Hyunwoo J. Kim
Human-Object Interaction detection is a holistic visual recognition task that entails object detection as well as interaction classification. Previous works of HOI detection has been addressed by the various compositions of subset predictions, e.g., Image -> HO -> I, Image -> HI -> O. Recently, transformer based architecture for HOI has emerged, which directly predicts the HOI triplets in an end-to-end fashion (Image -> HOI). Motivated by various inference paths for HOI detection, we propose cross-path consistency learning (CPC), which is a novel end-to-end learning strategy to improve HOI detection for transformers by leveraging augmented decoding paths. CPC learning enforces all the possible predictions from permuted inference sequences to be consistent. This simple scheme makes the model learn consistent representations, thereby improving generalization without increasing model capacity. Our experiments demonstrate the effectiveness of our method, and we achieved significant improvement on V-COCO and HICO-DET compared to the baseline models. Our code is available at https://github.com/mlvlab/CPChoi.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Human-Object Interaction Detection | HICO-DET | QPIC + CPC | mAP | 29.63 | #28 of 55 | Archive leaderboard | report |
| Human-Object Interaction Detection | HICO-DET | HOTR + CPC | mAP | 26.16 | #34 of 55 | Archive leaderboard | report |
| Human-Object Interaction Detection | V-COCO | QPIC + CPC | MAP | 63.1 | #33 of 34 | Archive leaderboard | report |
| Human-Object Interaction Detection | V-COCO | HOTR + CPC | MAP | 61.6 | #34 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