Abstract | ||
---|---|---|
How to use a deep convolutional neural network (CNN) to efficiently and effectively learn representations of a large unlabeled set of images and group them into clusters remains a challenging problem. To address this problem, we propose a Siamese clustering CNN (SC-CNN) to iteratively learn discriminative representations for image clustering. Based on the proposed SC-CNN, we employ a mini-batch-based joint pairwise representation learning and clustering scheme to make the computation and storage cost efficient for large-scale image clustering on a personal computer with a commercial GPU graphic card. On top of SC-CNN, the proposed pairwise learning scheme effectively learns discriminative representations by appropriately selecting same-cluster and different-cluster image pairs from the results of each clustering iteration. Experimental results demonstrate that the proposed method outperforms start-of-the-art clustering schemes in clustering accuracy on public image sets. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Unsupervised learning, image clustering, pairwise learning, deep learning, convolutional neural network |
Field | DocType | ISSN |
Pairwise comparison,Pattern recognition,Convolutional neural network,Visualization,Computer science,Personal computer,Feature extraction,Artificial intelligence,Cluster analysis,Discriminative model,Feature learning | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weng-Tai Su | 1 | 7 | 2.78 |
Chih-Chung Hsu | 2 | 125 | 11.31 |
Ziling Huang | 3 | 23 | 3.76 |
Chia-Wen Lin | 4 | 1639 | 120.23 |
Gene Cheung Connie Chan | 5 | 1387 | 121.82 |