Litcius/Paper detail

Remote Sensing Image Scene Classification with Noisy Label Distillation

Rui Zhang, Zhenghao Chen, Sanxing Zhang, Fei Song, Gang Zhang, Quancheng Zhou, Tao Leí

2020Remote Sensing25 citationsDOIOpen Access PDF

Abstract

The widespread applications of remote sensing image scene classification-based Convolutional Neural Networks (CNNs) are severely affected by the lack of large-scale datasets with clean annotations. Data crawled from the Internet or other sources allows for the most rapid expansion of existing datasets at a low-cost. However, directly training on such an expanded dataset can lead to network overfitting to noisy labels. Traditional methods typically divide this noisy dataset into multiple parts. Each part fine-tunes the network separately to improve performance further. These approaches are inefficient and sometimes even hurt performance. To address these problems, this study proposes a novel noisy label distillation method (NLD) based on the end-to-end teacher-student framework. First, unlike general knowledge distillation methods, NLD does not require pre-training on clean or noisy data. Second, NLD effectively distills knowledge from labels across a full range of noise levels for better performance. In addition, NLD can benefit from a fully clean dataset as a model distillation method to improve the student classifier’s performance. NLD is evaluated on three remote sensing image datasets, including UC Merced Land-use, NWPU-RESISC45, AID, in which a variety of noise patterns and noise amounts are injected. Experimental results show that NLD outperforms widely used directly fine-tuning methods and remote sensing pseudo-labeling methods.

Topics & Concepts

Computer scienceOverfittingDistillationConvolutional neural networkArtificial intelligenceClassifier (UML)Remote sensingMachine learningNoise (video)Pattern recognition (psychology)Contextual image classificationArtificial neural networkData miningImage (mathematics)Organic chemistryChemistryGeologyRemote-Sensing Image ClassificationMachine Learning and Data ClassificationAdvanced Image and Video Retrieval Techniques
Remote Sensing Image Scene Classification with Noisy Label Distillation | Litcius