paper-with-me

Papers

Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer

2020-05-18 · Yang Chen, Zongqing Lu, Xuechen Zhang, Lei Chen, Qingmin Liao

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.

📄 PDF Abstract BibTeX arXiv:2005.08806

Code (0)

등록된 구현이 없습니다.

Tasks

Disparity EstimationregressionStereo Matching

Similar Papers 제목 키워드 기반

Towards noise contrastive estimation with soft targets for conditional models

2024-04-22 · Johannes Hugger, Virginie Uhlmann

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

2023-06-27 · CVPR 2024 1 · Peng Xu, Zhiyu Xiang, Chenyu Qiao, Jingyun Fu 외

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 Matching

Evolving Loss Functions for Specific Image Augmentation Techniques

2024-04-09 · Brandon Morgan, Dean Hougen

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 Augmentation

Marginal Thresholding in Noisy Image Segmentation

2023-04-08 · Marcus Nordström, Henrik Hult, Atsuto Maki

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+1

Neural Loss Function Evolution for Large-Scale Image Classifier Convolutional Neural Networks

2024-01-30 · Brandon Morgan, Dean Hougen

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