Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking

TL;DR

This paper introduces a robust remote sensing scene classification method that iteratively corrects labels using multi-view voting and entropy ranking, improving accuracy despite initial label errors.

Contribution

It proposes a novel iterative learning approach combining multi-view voting and entropy-based ranking to enhance robustness against label noise in remote sensing image classification.

Findings

Outperforms existing methods on WHU-RS19 dataset

Effective in correcting label errors through voting and entropy ranking

Achieves higher classification accuracy with noisy labels

Abstract

Deep convolutional neural networks have been widely used in scene classification of remotely sensed images. In this work, we propose a robust learning method for the task that is secure against partially incorrect categorization of images. Specifically, we remove and correct errors in the labels progressively by iterative multi-view voting and entropy ranking. At each time step, we first divide the training data into disjoint parts for separate training and voting. The unanimity in the voting reveals the correctness of the labels, so that we can train a strong model with only the images with unanimous votes. In addition, we adopt entropy as an effective measure for prediction uncertainty, in order to partially recover labeling errors by ranking and selection. We empirically demonstrate the superiority of the proposed method on the WHU-RS19 dataset and the AID dataset.