Referring Camouflaged Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xuying, Yin, Bowen, Lin, Zheng, Hou, Qibin, Fan, Deng-Ping, Cheng, Ming-Ming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910888924020736
author Zhang, Xuying
Yin, Bowen
Lin, Zheng
Hou, Qibin
Fan, Deng-Ping
Cheng, Ming-Ming
author_facet Zhang, Xuying
Yin, Bowen
Lin, Zheng
Hou, Qibin
Fan, Deng-Ping
Cheng, Ming-Ming
contents We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scale dataset, called R2C7K, which consists of 7K images covering 64 object categories in real-world scenarios. Then, we develop a simple but strong dual-branch framework, dubbed R2CNet, with a reference branch embedding the common representations of target objects from referring images and a segmentation branch identifying and segmenting camouflaged objects under the guidance of the common representations. In particular, we design a Referring Mask Generation module to generate pixel-level prior mask and a Referring Feature Enrichment module to enhance the capability of identifying specified camouflaged objects. Extensive experiments show the superiority of our Ref-COD methods over their COD counterparts in segmenting specified camouflaged objects and identifying the main body of target objects. Our code and dataset are publicly available at https://github.com/zhangxuying1004/RefCOD.
format Preprint
id arxiv_https___arxiv_org_abs_2306_07532
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Referring Camouflaged Object Detection
Zhang, Xuying
Yin, Bowen
Lin, Zheng
Hou, Qibin
Fan, Deng-Ping
Cheng, Ming-Ming
Computer Vision and Pattern Recognition
We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scale dataset, called R2C7K, which consists of 7K images covering 64 object categories in real-world scenarios. Then, we develop a simple but strong dual-branch framework, dubbed R2CNet, with a reference branch embedding the common representations of target objects from referring images and a segmentation branch identifying and segmenting camouflaged objects under the guidance of the common representations. In particular, we design a Referring Mask Generation module to generate pixel-level prior mask and a Referring Feature Enrichment module to enhance the capability of identifying specified camouflaged objects. Extensive experiments show the superiority of our Ref-COD methods over their COD counterparts in segmenting specified camouflaged objects and identifying the main body of target objects. Our code and dataset are publicly available at https://github.com/zhangxuying1004/RefCOD.
title Referring Camouflaged Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.07532