Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection
This work addresses a critical limitation in HOI detection for computer vision applications, offering a solution to improve performance on rare interactions, though it is incremental as it builds on existing baselines.
The paper tackles the object bias problem in Human-Object Interaction (HOI) detection, where models perform poorly on rare interactions due to dataset imbalances, and proposes a plug-and-play Object-wise Debiasing Memory (ODM) method that achieves new state-of-the-art results on HICO-DET and HOI-COCO benchmarks, with significant improvements on rare interactions.
Detecting Human-Object Interaction (HOI) in images is an important step towards high-level visual comprehension. Existing work often shed light on improving either human and object detection, or interaction recognition. However, due to the limitation of datasets, these methods tend to fit well on frequent interactions conditioned on the detected objects, yet largely ignoring the rare ones, which is referred to as the object bias problem in this paper. In this work, we for the first time, uncover the problem from two aspects: unbalanced interaction distribution and biased model learning. To overcome the object bias problem, we propose a novel plug-and-play Object-wise Debiasing Memory (ODM) method for re-balancing the distribution of interactions under detected objects. Equipped with carefully designed read and write strategies, the proposed ODM allows rare interaction instances to be more frequently sampled for training, thereby alleviating the object bias induced by the unbalanced interaction distribution. We apply this method to three advanced baselines and conduct experiments on the HICO-DET and HOI-COCO datasets. To quantitatively study the object bias problem, we advocate a new protocol for evaluating model performance. As demonstrated in the experimental results, our method brings consistent and significant improvements over baselines, especially on rare interactions under each object. In addition, when evaluating under the conventional standard setting, our method achieves new state-of-the-art on the two benchmarks.