Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels

TL;DR

This paper introduces a novel framework for camouflaged object detection that leverages pseudo-edge and pseudo-map labels along with an uncertainty-aware refinement to improve boundary accuracy and overall detection performance.

Contribution

It proposes an uncertainty-based refinement module that effectively reduces noise in pseudo labels, enhancing camouflaged object detection accuracy.

Findings

Outperforms existing state-of-the-art COD methods

Effectively reduces boundary ambiguity in camouflaged object detection

Demonstrates robustness across various datasets

Abstract

This paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target object directly while outputting ambiguous camouflaged boundaries. On the other hand, the performance of the models considering edge information is not yet satisfactory. To this end, we propose a new framework that makes full use of multiple visual cues, i.e., saliency as well as edges, to refine the predicted camouflaged map. This framework consists of three key components, i.e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module. In particular, the pseudo-edge generator estimates the boundary that outputs the pseudo-edge label, and the conventional COD method serves as the pseudo-map generator that outputs the pseudo-map label. Then, we propose an uncertainty-based module to reduce the uncertainty and noise of such two pseudo labels, which takes both pseudo labels as input and outputs an edge-accurate camouflaged map. Experiments on various COD datasets demonstrate the effectiveness of our method with superior performance to the existing state-of-the-art methods.