Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer
Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms. Especially, matching cost volume, one of the most important procedure, is treated as a normal intermediate feature for the following softargmin regression, lacking explicit constraints compared with those traditional algorithms. In this paper, inspired by previous canonical definition of cost volume, we propose the noise-sampling cross entropy loss function to regularize the cost volume produced by deep neural networks to be unimodal and coherent. Extensive experiments validate that the proposed noise-sampling cross entropy loss can not only help neural networks learn more informative cost volume, but also lead to better stereo matching performance compared with several representative algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Disparity EstimationregressionStereo MatchingSimilar Papers 제목 키워드 기반
Towards noise contrastive estimation with soft targets for conditional models
Soft targets combined with the cross-entropy loss have shown to improve generalization performance of deep neural networks on supervised classification tasks. The standard cross-entropy loss however assumes data to be ca…
Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching
Despite the great success of deep learning in stereo matching, recovering accurate disparity maps is still challenging. Currently, L1 and cross-entropy are the two most widely used losses for stereo network training. Com…
Domain GeneralizationStereo MatchingEvolving Loss Functions for Specific Image Augmentation Techniques
Previous work in Neural Loss Function Search (NLFS) has shown a lack of correlation between smaller surrogate functions and large convolutional neural networks with massive regularization. We expand upon this research by…
Image AugmentationMarginal Thresholding in Noisy Image Segmentation
This work presents a study on label noise in medical image segmentation by considering a noise model based on Gaussian field deformations. Such noise is of interest because it yields realistic looking segmentations and b…
Image SegmentationMedical Image SegmentationOrgan SegmentationSegmentation+1Neural Loss Function Evolution for Large-Scale Image Classifier Convolutional Neural Networks
For classification, neural networks typically learn by minimizing cross-entropy, but are evaluated and compared using accuracy. This disparity suggests neural loss function search (NLFS), the search for a drop-in replace…
Image Augmentation