Deep Transformation-Invariant Clustering
Recent advances in image clustering typically focus on learning better deep representations. In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and performs clustering directly in image space. This learning process naturally fits in the gradient-based training of K-means and Gaussian mixture model, without requiring any additional loss or hyper-parameters. It leads us to two new deep transformation-invariant clustering frameworks, which jointly learn prototypes and transformations. More specifically, we use deep learning modules that enable us to resolve invariance to spatial, color and morphological transformations. Our approach is conceptually simple and comes with several advantages, including the possibility to easily adapt the desired invariance to the task and a strong interpretability of both cluster centers and assignments to clusters. We demonstrate that our novel approach yields competitive and highly promising results on standard image clustering benchmarks. Finally, we showcase its robustness and the advantages of its improved interpretability by visualizing clustering results over real photograph collections.
Code (1)
Tasks
ClusteringImage ClusteringUnsupervised Image ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enabling clustering algorithms to detect clusters of varying densities through scale-invariant data preprocessing
In this paper, we show that preprocessing data using a variant of rank transformation called 'Average Rank over an Ensemble of Sub-samples (ARES)' makes clustering algorithms robust to data representation and enable them…
ClusteringLearning Features and their Transformations by Spatial and Temporal Spherical Clustering
Learning features invariant to arbitrary transformations in the data is a requirement for any recognition system, biological or artificial. It is now widely accepted that simple cells in the primary visual cortex respond…
ClusteringInformation based Deep Clustering: An experimental study
Recently, two methods have shown outstanding performance for clustering images and jointly learning the feature representation. The first, called Information Maximiz-ing Self-Augmented Training (IMSAT), maximizes the mut…
ClusteringDeep ClusteringClustering by latent dimensions
This paper introduces a new clustering technique, called {\em dimensional clustering}, which clusters each data point by its latent {\em pointwise dimension}, which is a measure of the dimensionality of the data set loca…
ClusteringPose Invariant Person Re-Identification using Robust Pose-transformation GAN
The objective of person re-identification (re-ID) is to retrieve a person's images from an image gallery, given a single instance of the person of interest. Despite several advancements, learning discriminative identity-…
ClusteringImage GenerationPerson Re-Identification