Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification

TL;DR

This paper addresses the challenge of unsupervised fine-grained visual classification by proposing UFCL, a method that improves feature extraction, clustering, and contrastive learning, achieving state-of-the-art results across multiple datasets.

Contribution

The paper introduces UFCL, a novel approach combining a robust backbone, HDBSCAN clustering, and a weighted feature contrastive learning mechanism for unsupervised FGVC.

Findings

UFCL achieves state-of-the-art results on multiple FGVC datasets.

The use of HDBSCAN improves clustering quality for fine-grained categories.

The weighted feature agent enhances contrastive learning with noisy pseudo labels.

Abstract

Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose a simple, effective, and practical method, termed as UFCL, to alleviate the gap. Three key issues are concerned and improved: First, we introduce a robust and powerful backbone, ResNet50-IBN, which has an ability of domain adaptation when we transfer ImageNet pre-trained models to FGVC tasks. Next, we propose to introduce HDBSCAN instead of DBSCAN to do clustering, which can generate better clusters for adjacent categories with fewer hyper-parameters. Finally, we propose a weighted feature agent and its updating mechanism to do contrastive learning by using the pseudo labels with inevitable noise, which can improve the optimization process of learning the parameters of the network. The effectiveness of our UFCL is verified on CUB-200-2011, Oxford-Flowers, Oxford-Pets, Stanford-Dogs, Stanford-Cars and FGVC-Aircraft datasets. Under the unsupervised FGVC setting, we achieve state-of-the-art results, and analyze the key factors and the important parameters to provide a practical guidance.