Unsupervised Image Classification On Mnist
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| TURTLE (CLIP + DINOv2) | 97.8 | Let Go of Your Labels with Unsupervised Transfer | - |
| Adversarial AE | 95.9 | Adversarial Autoencoders | - |
| InfoGAN | 95 | InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets | - |
| IIC | 99.3 | Invariant Information Clustering for Unsupervised Image Classification and Segmentation | - |
| Bidirectional InfoGAN | 96.61 | Inferencing Based on Unsupervised Learning of Disentangled Representations | - |
| CatGAN | 95.73 | Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks | - |
| PixelGAN Autoencoders | 94.73 | PixelGAN Autoencoders | - |
| VMM | 96.74 | The VampPrior Mixture Model | - |
| ACOL + GAR + k-means | 98.32 | Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization | - |
| DTI-Clustering | 97.3 | Deep Transformation-Invariant Clustering | - |
0 of 10 row(s) selected.