Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
arXiv:2104.02628
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.
Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021. Aixuan Li and Jing Zhang contributed equally
References in corpus (9)
- Anabranch Network for Camouflaged Object Segmentation
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- Adversarial Learning for Semi-Supervised Semantic Segmentation
- Enhanced-alignment Measure for Binary Foreground Map Evaluation
- Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation
- Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
- Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
- Highly Efficient Salient Object Detection with 100K Parameters
- Uncertainty Inspired RGB-D Saliency Detection