Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

novel object recognition

Novel object recognition is a computer vision capability in which an automated system identifies and classifies visual objects belonging to categories that were not present in its labeled training dataset. Unlike traditional closed-set recognition models that are restricted to a fixed, predefined inventory of classes, systems equipped for novel object recognition generalize to unseen concepts without requiring new manual bounding-box annotations or model retraining. This is typically achieved through zero-shot learning and open-vocabulary frameworks that align visual features with semantic text representations in a shared multimodal embedding space, allowing the system to locate and categorize an unbounded variety of real-world objects based on textual descriptions or category names provided during inference.

1 item

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

Chuofan Ma, Yi Jiang, Xin Wen, Zehuan Yuan, Xiaojuan Qi

OrganizationsByteDanceUniversity of Hong Kong

Why you should read this

Proposes an open-vocabulary object detection framework that bypasses pre-aligned vision-language models by discovering co-occurring visual objects across captioned image groups to achieve state-of-the-art novel category detection on OV-LVIS.

Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained vision-language models for alignment, which are prone to limitations in localization accuracy or generalization capabilities. In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem. Intuitively, by grouping images that mention a shared concept in their captions, objects corresponding to the shared concept shall exhibit high co-occurrence among the group. CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept. Extensive experiments demonstrate that CoDet has superior performances and compelling scalability in open-vocabulary detection, e.g., by scaling up the visual backbone, CoDet achieves 37.0 AP_novel^m and 44.7 AP_all^m on OV-LVIS, surpassing the previous SoTA by 4.2 AP_novel^m and 9.8 AP_all^m. Code is available at https://github.com/CVMI-Lab/CoDet.

Added

2026-09-26