Clustering Images by Unmasking - A New Baseline
This work addresses clustering challenges in computer vision by introducing a novel method, though it is incremental as it applies an existing technique to a new domain.
The paper tackles image clustering by adapting the unmasking technique, previously used for text and video, to join clusters based on decreasing classifier accuracy, resulting in improved performance across various feature representations and tasks like digit recognition and fine-grained object classification.
We propose a novel agglomerative clustering method based on unmasking, a technique that was previously used for authorship verification of text documents and for abnormal event detection in videos. In order to join two clusters, we alternate between (i) training a binary classifier to distinguish between the samples from one cluster and the samples from the other cluster, and (ii) removing at each step the most discriminant features. The faster-decreasing accuracy rates of the intermediately-obtained classifiers indicate that the two clusters should be joined. To the best of our knowledge, this is the first work to apply unmasking in order to cluster images. We compare our method with k-means as well as a recent state-of-the-art clustering method. The empirical results indicate that our approach is able to improve performance for various (deep and shallow) feature representations and different tasks, such as handwritten digit recognition, texture classification and fine-grained object recognition.