Command Palette
Search for a command to run...
Junyuan Xie; Ross Girshick; Ali Farhadi
Abstract
Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| image-clustering-on-cifar-10 | DEC | ARI: 0.161 Accuracy: 0.301 Backbone: Custom NMI: 0.25 Train set: Train+Test |
| image-clustering-on-cifar-100 | DEC | Accuracy: 0.185 NMI: 0.136 Train Set: Train+Test |
| image-clustering-on-cmu-pie | DEC (KL based) | Accuracy: 0.801 NMI: 0.924 |
| image-clustering-on-imagenet-10 | DEC | Accuracy: 0.381 NMI: 0.282 |
| image-clustering-on-imagenet-dog-15 | DEC | Accuracy: 0.195 NMI: 0.122 |
| image-clustering-on-stl-10 | DEC | Accuracy: 0.359 NMI: 0.276 Train Split: Train+Test |
| image-clustering-on-tiny-imagenet | DEC | Accuracy: 0.037 NMI: 0.115 |
| image-clustering-on-youtube-faces-db | DEC (KL based) | Accuracy: 0.371 NMI: 0.446 |
| unsupervised-image-classification-on-svhn | DEC | # of clusters (k): 10 Acc: 11.90 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.