An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images
arXiv:1810.01163 · doi:10.1016/j.cviu.2019.102863
Abstract
Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In practice, collecting large scale accurately labeled datasets is a challenging and tedious task in most scenarios of remote sensing image analysis, thus cheap surrogate procedures are employed to label the dataset. Training deep neural networks on such datasets with inaccurate labels easily overfits to the noisy training labels and degrades the performance of the classification tasks drastically. To mitigate this effect, we propose an original solution with entropic optimal transportation. It allows to learn in an end-to-end fashion deep neural networks that are, to some extent, robust to inaccurately labeled samples. We empirically demonstrate on several remote sensing datasets, where both scene and pixel-based hyperspectral images are considered for classification. Our method proves to be highly tolerant to significant amounts of label noise and achieves favorable results against state-of-the-art methods.
arXiv commentUnder Consideration at Computer Vision and Image Understanding
References in corpus (23)
- Remote Sensing Image Scene Classification: Benchmark and State of the Art
- AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
- Understanding deep learning requires rethinking generalization
- Learning to Reweight Examples for Robust Deep Learning
- Training Deep Neural Networks on Noisy Labels with Bootstrapping
- PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
- Training Convolutional Networks with Noisy Labels
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning
- Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification
- Learning Aerial Image Segmentation from Online Maps
- Making Risk Minimization Tolerant to Label Noise
- High-Resolution Semantic Labeling with Convolutional Neural Networks
- Robust Loss Functions under Label Noise for Deep Neural Networks
- Stochastic Optimization for Large-scale Optimal Transport
- Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks
- Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
- Large-Scale Optimal Transport and Mapping Estimation
- Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance
- High-Resolution Multispectral Dataset for Semantic Segmentation
- TorontoCity: Seeing the World with a Million Eyes
- A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels
Cited by in corpus (4)
- On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification
- Sinkhorn Divergences for Unbalanced Optimal Transport
- Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
- A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data