Deep Clustering with Associative Memories
This addresses the problem of disjointed optimization in deep clustering for researchers in computer vision and text processing, offering an incremental improvement.
The paper tackled the disjointed nature of representation learning and clustering in deep clustering by proposing DCAM, a novel method using associative memories to integrate them into a single objective, resulting in improved clustering quality across architectures and data modalities.
Deep clustering - joint representation learning and latent space clustering - is a well studied problem especially in computer vision and text processing under the deep learning framework. While the representation learning is generally differentiable, clustering is an inherently discrete optimization task, requiring various approximations and regularizations to fit in a standard differentiable pipeline. This leads to a somewhat disjointed representation learning and clustering. In this work, we propose a novel loss function utilizing energy-based dynamics via Associative Memories to formulate a new deep clustering method, DCAM, which ties together the representation learning and clustering aspects more intricately in a single objective. Our experiments showcase the advantage of DCAM, producing improved clustering quality for various architecture choices (convolutional, residual or fully-connected) and data modalities (images or text).