CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection

Hojun Choi, Youngsun Lim, Jaeyo Shin, Hyunjung Shim

Keywords: Open Vocabulary, Object Detection, Pseudo-Labeling, Chain-of-Thought Reasoning

Abstract: Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to generalize to unseen classes without explicit supervision. However, these methods depend heavily on single-step image-text matching, neglecting the intermediate reasoning steps crucial for interpreting semantically complex visual contexts, such as crowding or occlusion. In this paper, we introduce CoT-PL, a framework that incorporates visual chain-of-thought reasoning into the pseudo-labeling process for OVD. It decomposes complex scene understanding into three interpretable steps---object localization, category recognition, and background grounding---where these intermediate reasoning states serve as rich supervision sources. Extensive experiments on standard OVD evaluation protocols demonstrate that CoT-PL achieves state-of-the-art performance with superior pseudo-labeling efficiency, outperforming the strong baseline by 9.4 AP$_{50}$ for novel classes on OV-COCO and improving box and mask AP$_r$ by 3.2 and 2.2, respectively, on OV-LVIS.

Previously Accepted: No

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 14