RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yu-Huan, Zhu, Zi-Xuan, Wang, Yan, Zhen, Liangli, Fan, Deng-Ping
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917105399496704
author Wu, Yu-Huan
Zhu, Zi-Xuan
Wang, Yan
Zhen, Liangli
Fan, Deng-Ping
author_facet Wu, Yu-Huan
Zhu, Zi-Xuan
Wang, Yan
Zhen, Liangli
Fan, Deng-Ping
contents Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at test time, which limits deployability and adds latency and data-collection burden. We introduce a Ref-COD framework that distills references into a class-prototype memory during training and synthesizes a reference vector at inference via a query-conditioned mixture of prototypes. Concretely, we maintain an EMA-updated prototype per category and predict mixture weights from the query to produce a guidance vector without any test-time references. To bridge the representation gap between reference statistics and camouflaged query features, we propose a bidirectional attention alignment module that adapts both the query features and the class representation. Thus, our approach yields a simple, efficient path to Ref-COD without mandatory references. We evaluate the proposed method on the large-scale R2C7K benchmark. Extensive experiments demonstrate competitive or superior performance of the proposed method compared with recent state-of-the-arts. Code is available at https://github.com/yuhuan-wu/RefOnce.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20989
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection
Wu, Yu-Huan
Zhu, Zi-Xuan
Wang, Yan
Zhen, Liangli
Fan, Deng-Ping
Computer Vision and Pattern Recognition
Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at test time, which limits deployability and adds latency and data-collection burden. We introduce a Ref-COD framework that distills references into a class-prototype memory during training and synthesizes a reference vector at inference via a query-conditioned mixture of prototypes. Concretely, we maintain an EMA-updated prototype per category and predict mixture weights from the query to produce a guidance vector without any test-time references. To bridge the representation gap between reference statistics and camouflaged query features, we propose a bidirectional attention alignment module that adapts both the query features and the class representation. Thus, our approach yields a simple, efficient path to Ref-COD without mandatory references. We evaluate the proposed method on the large-scale R2C7K benchmark. Extensive experiments demonstrate competitive or superior performance of the proposed method compared with recent state-of-the-arts. Code is available at https://github.com/yuhuan-wu/RefOnce.
title RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20989