Unsupervised Image Classification for Deep Representation Learning
Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component, embedding clustering, limits its extension to the extremely large-scale dataset due to its prerequisite to save the global latent embedding of the entire dataset. In this work, we aim to make this framework more simple and elegant without performance decline. We propose an unsupervised image classification framework without using embedding clustering, which is very similar to standard supervised training manner. For detailed interpretation, we further analyze its relation with deep clustering and contrastive learning. Extensive experiments on ImageNet dataset have been conducted to prove the effectiveness of our method. Furthermore, the experiments on transfer learning benchmarks have verified its generalization to other downstream tasks, including multi-label image classification, object detection, semantic segmentation and few-shot image classification.
PDF Abstract
Tasks
Classification
Clustering
Contrastive Learning
Deep Clustering
Few-Shot Image Classification
General Classification
Image Classification
Image Clustering
Multi-Label Image Classification
object-detection
Object Detection
Representation Learning
Self-Supervised Learning
Semantic Segmentation
Transfer Learning
Unsupervised Image Classification
