Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images

Abstract

Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the State-of-the-Art image clustering models, achieving accuracy performance gains ranging from $2.1\%$ to $15.9\%$. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote--sensing images.

arXiv comment39

References in corpus (17)

• A Simple Framework for Contrastive Learning of Visual Representations
• Natural Scales in Geographical Patterns
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
• Unsupervised Representation Learning by Predicting Image Rotations
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
• Deep Clustering for Unsupervised Learning of Visual Features
• Large Scale Adversarial Representation Learning
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• Diversity in Machine Learning
• SPICE: Semantic Pseudo-labeling for Image Clustering
• Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images
• Improvements to context based self-supervised learning
• Self-labelling via simultaneous clustering and representation learning
• Unsupervised Deep Learning by Neighbourhood Discovery
• Controllable Invariance through Adversarial Feature Learning