Uncertainty-aware Joint Salient Object and Camouflaged Object Detection

By Aixuan Li, Jing Zhang, Yun-Qiu Lv, Bowen Liu, Tong Zhang, Yuchao Dai. Computer Vision and Pattern Recognition, 2021

300 citations recorded by the source corpus.

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 lever-aging 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 tasks1.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/05c77ccfc785abd31f38f3b46bafb81f786f871f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. Deng-Ping Fan
2. Xiaoqi Zhao
3. Youwei Pang
4. Yuchao Dai
5. Jing Zhang
6. Aixuan Li
7. Bowen Liu
8. Huchuan Lu

In Computer Vision and Pattern Recognition

1. Deng-Ping Fan
2. Xiaoqi Zhao
3. Youwei Pang
4. Ling Shao
5. Yuchao Dai
6. Huchuan Lu
7. Jing Zhang
8. Aixuan Li

Citations in the corpus

• Simultaneously Localize, Segment and Rank the Camouflaged Objects (2021, methodology): “Existing camouflaged object detection models [10, 22, 61, 33, 25] are designed based on binary ground truth camouflaged object datasets [22, 10, 44] as shown in Fig.”
• Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (2022, methodology): “Some uncertainty-aware methods [20, 47] are proposed to model and cope with the uncertainty in data annotation or COD data itself.”