Uncertainty-aware Joint Salient Object and Camouflaged Object Detection

TL;DR

This paper introduces a novel framework that leverages the contradictory nature of salient and camouflaged object detection to improve both tasks through uncertainty modeling and adversarial learning, achieving state-of-the-art results.

Contribution

It proposes a new paradigm that exploits the relationship between SOD and COD, incorporating similarity measures and uncertainty estimation to enhance detection robustness.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively models the contradiction between SOD and COD.

Improves robustness of both detection tasks through uncertainty-aware learning.

Abstract

Visual salient object detection (SOD) aims at finding the salient object(s) that attract human attention, while camouflaged object detection (COD) on the contrary intends to discover the camouflaged object(s) that hidden in the surrounding. In this paper, we propose a paradigm of leveraging the contradictory information to enhance the detection ability of both salient object detection and camouflaged object detection. We start by exploiting the easy positive samples in the COD dataset to serve as hard positive samples in the SOD task to improve the robustness of the SOD model. Then, we introduce a similarity measure module to explicitly model the contradicting attributes of these two tasks. Furthermore, considering the uncertainty of labeling in both tasks' datasets, we propose an adversarial learning network to achieve both higher order similarity measure and network confidence estimation. Experimental results on benchmark datasets demonstrate that our solution leads to state-of-the-art (SOTA) performance for both tasks.