Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection
This work addresses a domain-specific problem in computer vision for HOI detection, offering an incremental improvement through a novel learning strategy.
The paper tackles the problem of improving Human-Object Interaction detection in transformers by proposing cross-path consistency learning, which enforces consistency across augmented decoding paths, resulting in significant improvements on V-COCO and HICO-DET benchmarks compared to baselines.
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.