Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yitong, Yao, Wenhao, Meng, Lingchen, Wu, Sihong, Wu, Zuxuan, Jiang, Yu-Gang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916540274704384
author Chen, Yitong
Yao, Wenhao
Meng, Lingchen
Wu, Sihong
Wu, Zuxuan
Jiang, Yu-Gang
author_facet Chen, Yitong
Yao, Wenhao
Meng, Lingchen
Wu, Sihong
Wu, Zuxuan
Jiang, Yu-Gang
contents Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories. However, when the scale of the category vocabularies during training expands to a real-world level, previous classifiers aligned with coarse class names significantly reduce the recognition performance of these detectors. In this paper, we introduce Prova, a multi-modal prototype classifier for vast-vocabulary object detection. Prova extracts comprehensive multi-modal prototypes as initialization of alignment classifiers to tackle the vast-vocabulary object recognition failure problem. On V3Det, this simple method greatly enhances the performance among one-stage, two-stage, and DETR-based detectors with only additional projection layers in both supervised and open-vocabulary settings. In particular, Prova improves Faster R-CNN, FCOS, and DINO by 3.3, 6.2, and 2.9 AP respectively in the supervised setting of V3Det. For the open-vocabulary setting, Prova achieves a new state-of-the-art performance with 32.8 base AP and 11.0 novel AP, which is of 2.6 and 4.3 gain over the previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17800
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection
Chen, Yitong
Yao, Wenhao
Meng, Lingchen
Wu, Sihong
Wu, Zuxuan
Jiang, Yu-Gang
Computer Vision and Pattern Recognition
Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories. However, when the scale of the category vocabularies during training expands to a real-world level, previous classifiers aligned with coarse class names significantly reduce the recognition performance of these detectors. In this paper, we introduce Prova, a multi-modal prototype classifier for vast-vocabulary object detection. Prova extracts comprehensive multi-modal prototypes as initialization of alignment classifiers to tackle the vast-vocabulary object recognition failure problem. On V3Det, this simple method greatly enhances the performance among one-stage, two-stage, and DETR-based detectors with only additional projection layers in both supervised and open-vocabulary settings. In particular, Prova improves Faster R-CNN, FCOS, and DINO by 3.3, 6.2, and 2.9 AP respectively in the supervised setting of V3Det. For the open-vocabulary setting, Prova achieves a new state-of-the-art performance with 32.8 base AP and 11.0 novel AP, which is of 2.6 and 4.3 gain over the previous methods.
title Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.17800