Published March 18, 2022 | Version v1
Journal article Open

Fine-Grained Adversarial Semi-supervised Learning

Description

In this paper we exploit Semi-Supervised Learning (SSL) to increase the amount of training data to improve the performance of
Fine-Grained Visual Categorization (FGVC). This problem has not been investigated in the past in spite of prohibitive annotation costs that FGVC requires. Our approach leverages unlabeled data with an adversarial optimization strategy in which the internal features representation is obtained with a second-order pooling model. This combination allows to back-propagate the information of the parts, represented by second-order pooling, onto unlabeled data in an adversarial training setting. We demonstrate the effectiveness of the combined use by conducting experiments on six state-of-the-art fi ne-grained datasets, which include Aircrafts, Stanford Cars, CUB-200-2011, Oxford Flowers, Stanford Dogs, and the recent Semi-Supervised iNaturalist-Aves. Experimental results clearly show that our proposed method has better performance than the only previous approach that examined this problem; it also obtained higher classification accuracy with respect to the supervised learning methods with which we compared.

Files

TOMM-adversarial-fine-grained.pdf

Files (3.1 MB)

Name Size Download all
md5:8cb25cc8039960b7e30a878d2878c260
3.1 MB Preview Download

Additional details

Funding

AI4Media – A European Excellence Centre for Media, Society and Democracy 951911
European Commission