The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an end-to-end fashion, providing direct cluster assignments of images without additional processing. Multi-Modal Deep Clustering (MMDC), trains a deep network to align its image embeddings with target points sampled from a Gaussian Mixture Model distribution. The cluster assignments are then determined by mixture component association of image embeddings. Simultaneously, the same deep network is trained to solve an additional self-supervised task of predicting image rotations. This pushes the network to learn more meaningful image representations that facilitate a better clustering. Experimental results show that MMDC achieves or exceeds state-of-the-art performance on six challenging benchmarks. On natural image datasets we improve on previous results with significant margins of up to 20% absolute accuracy points, yielding an accuracy of 82% on CIFAR-10, 45% on CIFAR-100 and 69% on STL-10.
|Original language||American English|
|Title of host publication||Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||8|
|State||Published - 2020|
|Event||25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy|
Duration: 10 Jan 2021 → 15 Jan 2021
|Name||Proceedings - International Conference on Pattern Recognition|
|Conference||25th International Conference on Pattern Recognition, ICPR 2020|
|Period||10/01/21 → 15/01/21|
Bibliographical noteFunding Information:
This work was supported in part by a grant from the Israel Science Foundation (ISF) and by the Gatsby Charitable Foundations.
© 2020 IEEE