Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement

Abstract

Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. But one distinct advantage of unsupervised over supervised learning is that the former possesses more variety and freedom in designing the objective. In this work, we explore new dimensions of unsupervised learning by proposing the Progressive Stage-wise Learning (PSL) framework. For a given unsupervised task, we design multilevel tasks and define different learning stages for the deep network. Early learning stages are forced to focus on lowlevel tasks while late stages are guided to extract deeper information through harder tasks. We discover that by progressive stage-wise learning, unsupervised feature representation can be effectively enhanced. Our extensive experiments show that PSL consistently improves results for the leading unsupervised learning methods.

arXiv commentAccepted by the IEEE conference on computer vision and pattern recognition. 2021

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• Improved Baselines with Momentum Contrastive Learning
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Contrastive Multiview Coding
• Prototypical Contrastive Learning of Unsupervised Representations
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
• Self Paced Deep Learning for Weakly Supervised Object Detection
• Self-labelling via simultaneous clustering and representation learning