Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection

TL;DR

This paper introduces InterProDa, a novel prompt distribution learning method that enhances human-object interaction detection by better representing intra-category diversity and inter-category relationships, leading to improved performance.

Contribution

The paper proposes InterProDa, a new approach that learns multiple soft prompts and category distributions to improve HOI detection, adaptable to existing transformer-based detectors.

Findings

Achieves competitive results on HICO-DET and V-COCO benchmarks.

Enhances existing HOI detectors with minimal additional parameters.

Effectively models intra-category diversity and cross-category relationships.

Abstract

Human-object interaction (HOI) detectors with popular query-transformer architecture have achieved promising performance. However, accurately identifying uncommon visual patterns and distinguishing between ambiguous HOIs continue to be difficult for them. We observe that these difficulties may arise from the limited capacity of traditional detector queries in representing diverse intra-category patterns and inter-category dependencies. To address this, we introduce the Interaction Prompt Distribution Learning (InterProDa) approach. InterProDa learns multiple sets of soft prompts and estimates category distributions from various prompts. It then incorporates HOI queries with category distributions, making them capable of representing near-infinite intra-category dynamics and universal cross-category relationships. Our InterProDa detector demonstrates competitive performance on HICO-DET and vcoco benchmarks. Additionally, our method can be integrated into most transformer-based HOI detectors, significantly enhancing their performance with minimal additional parameters.