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

TL;DR

RefOnce introduces a reference distillation method that creates a prototype memory during training, enabling camouflaged object detection without needing reference images at test time, thus improving efficiency and deployability.

Contribution

The paper proposes a novel framework that distills references into a prototype memory, allowing reference-free inference for camouflaged object detection.

Findings

Achieves competitive or superior performance on R2C7K benchmark.

Eliminates the need for reference images during testing.

Provides an efficient and deployable solution for Ref-COD.

Abstract

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.