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

10/29/2021
by   Nobukatsu Kajiura, et al.
0

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.

READ FULL TEXT

page 2

page 3

page 6

research
08/28/2021

Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection

This work tackles the unsupervised cross-domain object detection problem...
research
06/04/2023

Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection

Semi-supervised object detection (SSOD) has made significant progress wi...
research
12/03/2021

MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection

Weakly supervised salient object detection (WSOD) targets to train a CNN...
research
04/23/2021

STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains

We propose an unsupervised domain adaptation (UDA) approach for white ma...
research
12/08/2020

3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection

3D object detection is an important yet demanding task that heavily reli...
research
08/25/2020

Label Decoupling Framework for Salient Object Detection

To get more accurate saliency maps, recent methods mainly focus on aggre...
research
02/08/2022

Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling

Salient object detection has been long studied to identify the most visu...

Please sign up or login with your details

Forgot password? Click here to reset