SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zishuo, Zhou, Wenhao, Xu, Jinglin, Peng, Yuxin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917796550541312
author Wang, Zishuo
Zhou, Wenhao
Xu, Jinglin
Peng, Yuxin
author_facet Wang, Zishuo
Zhou, Wenhao
Xu, Jinglin
Peng, Yuxin
contents Open-vocabulary detection (OVD) aims to detect novel objects without instance-level annotations to achieve open-world object detection at a lower cost. Existing OVD methods mainly rely on the powerful open-vocabulary image-text alignment capability of Vision-Language Pretrained Models (VLM) such as CLIP. However, CLIP is trained on image-text pairs and lacks the perceptual ability for local regions within an image, resulting in the gap between image and region representations. Directly using CLIP for OVD causes inaccurate region classification. We find the image-region gap is primarily caused by the deformation of region feature maps during region of interest (RoI) extraction. To mitigate the inaccurate region classification in OVD, we propose a new Shape-Invariant Adapter named SIA-OVD to bridge the image-region gap in the OVD task. SIA-OVD learns a set of feature adapters for regions with different shapes and designs a new adapter allocation mechanism to select the optimal adapter for each region. The adapted region representations can align better with text representations learned by CLIP. Extensive experiments demonstrate that SIA-OVD effectively improves the classification accuracy for regions by addressing the gap between images and regions caused by shape deformation. SIA-OVD achieves substantial improvements over representative methods on the COCO-OVD benchmark. The code is available at https://github.com/PKU-ICST-MIPL/SIA-OVD_ACMMM2024.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05650
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
Wang, Zishuo
Zhou, Wenhao
Xu, Jinglin
Peng, Yuxin
Computer Vision and Pattern Recognition
Multimedia
I.2.10
Open-vocabulary detection (OVD) aims to detect novel objects without instance-level annotations to achieve open-world object detection at a lower cost. Existing OVD methods mainly rely on the powerful open-vocabulary image-text alignment capability of Vision-Language Pretrained Models (VLM) such as CLIP. However, CLIP is trained on image-text pairs and lacks the perceptual ability for local regions within an image, resulting in the gap between image and region representations. Directly using CLIP for OVD causes inaccurate region classification. We find the image-region gap is primarily caused by the deformation of region feature maps during region of interest (RoI) extraction. To mitigate the inaccurate region classification in OVD, we propose a new Shape-Invariant Adapter named SIA-OVD to bridge the image-region gap in the OVD task. SIA-OVD learns a set of feature adapters for regions with different shapes and designs a new adapter allocation mechanism to select the optimal adapter for each region. The adapted region representations can align better with text representations learned by CLIP. Extensive experiments demonstrate that SIA-OVD effectively improves the classification accuracy for regions by addressing the gap between images and regions caused by shape deformation. SIA-OVD achieves substantial improvements over representative methods on the COCO-OVD benchmark. The code is available at https://github.com/PKU-ICST-MIPL/SIA-OVD_ACMMM2024.
title SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
topic Computer Vision and Pattern Recognition
Multimedia
I.2.10
url https://arxiv.org/abs/2410.05650