Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection

TL;DR

This paper introduces RISE, a novel unsupervised paradigm for camouflaged object detection that leverages dataset-level context and prototype libraries to generate pseudo-labels without annotations, significantly improving detection performance.

Contribution

The paper proposes RISE, a self-augmented unsupervised framework that constructs prototype libraries and uses multi-view KNN retrieval to enhance camouflaged object detection without requiring annotations.

Findings

RISE outperforms state-of-the-art unsupervised methods.

The clustering-then-retrieval strategy improves prototype quality.

Multi-view KNN retrieval enhances pseudo-mask robustness.

Abstract

At the core of Camouflaged Object Detection (COD) lies segmenting objects from their highly similar surroundings. Previous efforts navigate this challenge primarily through image-level modeling or annotation-based optimization. Despite advancing considerably, this commonplace practice hardly taps valuable dataset-level contextual information or relies on laborious annotations. In this paper, we propose RISE, a RetrIeval SElf-augmented paradigm that exploits the entire training dataset to generate pseudo-labels for single images, which could be used to train COD models. RISE begins by constructing prototype libraries for environments and camouflaged objects using training images (without ground truth), followed by K-Nearest Neighbor (KNN) retrieval to generate pseudo-masks for each image based on these libraries. It is important to recognize that using only training images without annotations exerts a pronounced challenge in crafting high-quality prototype libraries. In this light, we introduce a Clustering-then-Retrieval (CR) strategy, where coarse masks are first generated through clustering, facilitating subsequent histogram-based image filtering and cross-category retrieval to produce high-confidence prototypes. In the KNN retrieval stage, to alleviate the effect of artifacts in feature maps, we propose Multi-View KNN Retrieval (MVKR), which integrates retrieval results from diverse views to produce more robust and precise pseudo-masks. Extensive experiments demonstrate that RISE outperforms state-of-the-art unsupervised and prompt-based methods. Code is available at https://github.com/xiaohainku/RISE.