Fine-Grained Adversarial Semi-supervised Learning

TL;DR

This paper introduces a semi-supervised adversarial learning approach using second-order pooling for fine-grained visual categorization, effectively leveraging unlabeled data to improve classification accuracy.

Contribution

It proposes a novel adversarial semi-supervised learning method with second-order pooling for FGVC, addressing annotation cost issues and outperforming previous approaches.

Findings

Outperforms previous semi-supervised methods on six fine-grained datasets.

Achieves higher accuracy than supervised learning baselines.

Effectively utilizes unlabeled data to enhance classification performance.

Abstract

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 fine-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.