Predictive Uncertainty Estimation for Camouflaged Object Detection
- 22 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 3580-3591
Abstract
Uncertainty is inherent in machine learning methods, especially those for camouflaged object detection aiming to finely segment the objects concealed in background. The strong “center bias” of the training dataset leads to models of poor generalization ability as the models learn to find camouflaged objects around image center, which we define as “model bias”. Further, due to the similar appearance of camouflaged object and its surroundings, it is difficult to label the accurate scope of the camouflaged object, especially along object boundaries, which we term as “data bias”. To effectively model the two types of biases, we resort to uncertainty estimation and introduce predictive uncertainty estimation technique, which is the sum of model uncertainty and data uncertainty, to estimate the two types of biases simultaneously. Specifically, we present a predictive uncertainty estimation network ( PUENet ) that consists of a Bayesian conditional variational auto-encoder (BCVAE) to achieve predictive uncertainty estimation, and a predictive uncertainty approximation (PUA) module to avoid the expensive sampling process at test-time. Experimental results show that our PUENet achieves both highly accurate prediction, and reliable uncertainty estimation representing the biases within both model parameters and the datasets.Keywords
Funding Information
- Chinese Scholarship Council
This publication has 63 references indexed in Scilit:
- Learning to Detect Salient Objects with Image-Level Supervision2017
- Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach2017
- DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye FixationsIEEE Transactions on Image Processing, 2017
- Multiclass Learning With Partially Corrupted LabelsIEEE Transactions on Neural Networks and Learning Systems, 2017
- Learning Deep Networks from Noisy Labels with Dropout Regularization2016
- It’s Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos2016
- Deep Residual Learning for Image Recognition2016
- End-to-End Saliency Mapping via Probability Distribution Prediction2016
- The Secrets of Salient Object Segmentation2014
- Learning to predict where humans look2009