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 larg...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-08
Main Authors: Chen, Weijie, Pu, Shiliang, Xie, Di, Yang, Shicai, Guo, Yilu, Lin, Luojun
Format: Article
Language:English
Subjects:
Classification
Clustering
Datasets
Embedding
Image classification
Image detection
Image segmentation
Object recognition
Representations
Supervised learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422