Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection

TL;DR

This paper introduces MMC-Det, a novel framework that leverages multi-modal contextual knowledge through distillation to improve open-vocabulary object detection, effectively understanding novel categories by integrating visual and language cues.

Contribution

The paper proposes a multi-modal contextual knowledge distillation framework, MMC-Det, which transfers knowledge from a teacher transformer to a student detector for enhanced open-vocabulary detection.

Findings

Outperforms recent state-of-the-art methods on various datasets.

Effectively incorporates multi-modal contextual knowledge into object detection.

Demonstrates significant improvements in detecting novel categories.

Abstract

In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint relationship across regions and words. However, it is challenging to incorporate such multi-modal contextual knowledge into OVD. The reason is that previous detection frameworks fail to jointly model multi-modal contextual knowledge, as object detectors only support vision inputs and no caption description is provided at test time. To this end, we propose a multi-modal contextual knowledge distillation framework, MMC-Det, to transfer the learned contextual knowledge from a teacher fusion transformer with diverse multi-modal masked language modeling (D-MLM) to a student detector. The diverse multi-modal masked language modeling is realized by an object divergence constraint upon traditional multi-modal masked language modeling (MLM), in order to extract fine-grained region-level visual contexts, which are vital to object detection. Extensive experiments performed upon various detection datasets show the effectiveness of our multi-modal context learning strategy, where our approach well outperforms the recent state-of-the-art methods.