Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking
This work addresses label noise in remote sensing scene classification, which is an incremental improvement for domain-specific applications.
The paper tackles the problem of partially incorrect labels in remote sensing scene classification by proposing a robust learning method that progressively removes and corrects errors using iterative multi-view voting and entropy ranking, achieving superior performance on the WHU-RS19 and AID datasets.
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.