Reformulating HOI Detection as Adaptive Set Prediction

Abstract

Determining which image regions to concentrate is critical for Human-Object Interaction (HOI) detection. Conventional HOI detectors focus on either detected human and object pairs or pre-defined interaction locations, which limits learning of the effective features. In this paper, we reformulate HOI detection as an adaptive set prediction problem, with this novel formulation, we propose an Adaptive Set-based one-stage framework (AS-Net) with parallel instance and interaction branches. To attain this, we map a trainable interaction query set to an interaction prediction set with transformer. Each query adaptively aggregates the interaction-relevant features from global contexts through multi-head co-attention. Besides, the training process is supervised adaptively by matching each ground-truth with the interaction prediction. Furthermore, we design an effective instance-aware attention module to introduce instructive features from the instance branch into the interaction branch. Our method outperforms previous stateof-the-art methods without any extra human pose and language features on three challenging HOI detection datasets. Especially, we achieve over 31% relative improvement on a large scale HICO-DET dataset. Code is available at https://github.com/yoyomimi/AS-Net.

Instances as Queries

“…Trackformer [35] and Transtrack [41] build a query based multiple object tracktor upon DETR and Deformable DETR, respectively, and attain comparable results to the non-query based methods. AS-Net [11] introduces a query based set-prediction pipeline to human object interaction and obtains promising results. Despite query based setprediction method is being widely used to many computer vision tasks, few efforts are conducted to build a successful query based instance segmentation framework.…”