HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models

TL;DR

HOICLIP introduces a novel framework that leverages CLIP's visual and textual knowledge for improved human-object interaction detection, especially in few/zero-shot scenarios, with a new interaction decoder and knowledge integration techniques.

Contribution

The paper proposes a new HOI detection method that efficiently extracts and integrates CLIP's visual and textual knowledge, improving generalization and performance over existing approaches.

Findings

Outperforms state-of-the-art by +4.04 mAP on HICO-Det.

Effective knowledge extraction from CLIP enhances HOI detection.

Achieves better generalization in few/zero-shot scenarios.

Abstract

Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Recently, Contrastive Language-Image Pre-training (CLIP) has shown great potential in providing interaction prior for HOI detectors via knowledge distillation. However, such approaches often rely on large-scale training data and suffer from inferior performance under few/zero-shot scenarios. In this paper, we propose a novel HOI detection framework that efficiently extracts prior knowledge from CLIP and achieves better generalization. In detail, we first introduce a novel interaction decoder to extract informative regions in the visual feature map of CLIP via a cross-attention mechanism, which is then fused with the detection backbone by a knowledge integration block for more accurate human-object pair detection. In addition, prior knowledge in CLIP text encoder is leveraged to generate a classifier by embedding HOI descriptions. To distinguish fine-grained interactions, we build a verb classifier from training data via visual semantic arithmetic and a lightweight verb representation adapter. Furthermore, we propose a training-free enhancement to exploit global HOI predictions from CLIP. Extensive experiments demonstrate that our method outperforms the state of the art by a large margin on various settings, e.g. +4.04 mAP on HICO-Det. The source code is available in https://github.com/Artanic30/HOICLIP.