Open-Vocabulary Object Detection via Neighboring Region Attention Alignment

TL;DR

This paper introduces Neighboring Region Attention Alignment (NRAA), a novel method that enhances open-vocabulary object detection by leveraging neighboring region relationships through attention mechanisms, improving alignment with vision-language models.

Contribution

The paper proposes NRAA, a new attention-based alignment method that considers neighboring regions to improve open-vocabulary object detection performance.

Findings

NRAA outperforms existing distillation-based methods on open-vocabulary benchmarks.

Incorporating neighboring region attention improves detection accuracy for novel classes.

Extensive experiments demonstrate the effectiveness of NRAA in real-world scenarios.

Abstract

The nature of diversity in real-world environments necessitates neural network models to expand from closed category settings to accommodate novel emerging categories. In this paper, we study the open-vocabulary object detection (OVD), which facilitates the detection of novel object classes under the supervision of only base annotations and open-vocabulary knowledge. However, we find that the inadequacy of neighboring relationships between regions during the alignment process inevitably constrains the performance on recent distillation-based OVD strategies. To this end, we propose Neighboring Region Attention Alignment (NRAA), which performs alignment within the attention mechanism of a set of neighboring regions to boost the open-vocabulary inference. Specifically, for a given proposal region, we randomly explore the neighboring boxes and conduct our proposed neighboring region attention (NRA) mechanism to extract relationship information. Then, this interaction information is seamlessly provided into the distillation procedure to assist the alignment between the detector and the pre-trained vision-language models (VLMs). Extensive experiments validate that our proposed model exhibits superior performance on open-vocabulary benchmarks.