Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

TL;DR

This paper introduces the Unary-Pairwise Transformer, a two-stage human-object interaction detector that leverages unary and pairwise representations, outperforming existing methods while being more efficient and approaching real-time performance.

Contribution

The paper presents a novel two-stage transformer-based HOI detection model that exploits unary and pairwise features, demonstrating superior performance and efficiency over existing one-stage methods.

Findings

Outperforms state-of-the-art on HICO-DET and V-COCO datasets.

Achieves near real-time inference with ResNet50.

More memory-efficient and faster training than comparable models.

Abstract

Recent developments in transformer models for visual data have led to significant improvements in recognition and detection tasks. In particular, using learnable queries in place of region proposals has given rise to a new class of one-stage detection models, spearheaded by the Detection Transformer (DETR). Variations on this one-stage approach have since dominated human-object interaction (HOI) detection. However, the success of such one-stage HOI detectors can largely be attributed to the representation power of transformers. We discovered that when equipped with the same transformer, their two-stage counterparts can be more performant and memory-efficient, while taking a fraction of the time to train. In this work, we propose the Unary-Pairwise Transformer, a two-stage detector that exploits unary and pairwise representations for HOIs. We observe that the unary and pairwise parts of our transformer network specialise, with the former preferentially increasing the scores of positive examples and the latter decreasing the scores of negative examples. We evaluate our method on the HICO-DET and V-COCO datasets, and significantly outperform state-of-the-art approaches. At inference time, our model with ResNet50 approaches real-time performance on a single GPU.