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

MAKE IMPACT

Jiabao Wang , Yang Li , Xiu-Shen Wei , Hang Li , Zhuang Miao , Rui Zhang · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2203.00441

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.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2203.00441

PDF

https://arxiv.org/pdf/2203.00441

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4221142651

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4221142651

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2203.00441

Digital Object Identifier

Title

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

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-03-01

Full publication date if available

Authors

Jiabao Wang, Yang Li, Xiu-Shen Wei, Hang Li, Zhuang Miao, Rui Zhang

List of authors in order

Landing page

https://arxiv.org/abs/2203.00441

Publisher landing page

PDF URL

https://arxiv.org/pdf/2203.00441

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2203.00441

Direct OA link when available

Concepts

Artificial intelligence, Unsupervised learning, Computer science, Machine learning, Cluster analysis, Transfer of learning, Supervised learning, Bridge (graph theory), Key (lock), Feature learning, Deep learning, Artificial neural network, Pattern recognition (psychology), Computer security, Internal medicine, Medicine

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2022: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload