End-to-End Human Object Interaction Detection with HOI Transformer

TL;DR

HOI Transformer introduces an end-to-end, simplified approach for human object interaction detection that directly predicts interactions from global image context, outperforming previous methods in accuracy.

Contribution

The paper presents HOI Transformer, a novel end-to-end model that eliminates hand-designed components and directly predicts HOI instances using global context reasoning.

Findings

Achieves 26.61% AP on HICO-DET

Achieves 52.9% AP_role on V-COCO

Outperforms previous methods in accuracy

Abstract

We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner. Current approaches either decouple HOI task into separated stages of object detection and interaction classification or introduce surrogate interaction problem. In contrast, our method, named HOI Transformer, streamlines the HOI pipeline by eliminating the need for many hand-designed components. HOI Transformer reasons about the relations of objects and humans from global image context and directly predicts HOI instances in parallel. A quintuple matching loss is introduced to force HOI predictions in a unified way. Our method is conceptually much simpler and demonstrates improved accuracy. Without bells and whistles, HOI Transformer achieves $26.61\% $ $ AP $ on HICO-DET and $52.9\%$ $AP_{role}$ on V-COCO, surpassing previous methods with the advantage of being much simpler. We hope our approach will serve as a simple and effective alternative for HOI tasks. Code is available at https://github.com/bbepoch/HoiTransformer .