Learning Gabor Texture Features for Fine-Grained Recognition

TL;DR

This paper introduces a novel texture feature extraction method using Gabor filters, integrated with CNNs, to improve fine-grained recognition by capturing detailed local and multi-frequency features, achieving state-of-the-art results.

Contribution

The paper proposes a Gabor filter-based texture branch with optimized parameters and a statistical feature extractor, enhancing CNNs for fine-grained recognition.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively captures multi-frequency and local texture details.

Enhances CNN features with Gabor-based texture information.

Abstract

Extracting and using class-discriminative features is critical for fine-grained recognition. Existing works have demonstrated the possibility of applying deep CNNs to exploit features that distinguish similar classes. However, CNNs suffer from problems including frequency bias and loss of detailed local information, which restricts the performance of recognizing fine-grained categories. To address the challenge, we propose a novel texture branch as complimentary to the CNN branch for feature extraction. We innovatively utilize Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filters in effectively capturing multi-frequency features and detailed local information. We implement several designs to enhance the effectiveness of Gabor filters, including imposing constraints on parameter values and developing a learning method to determine the optimal parameters. Moreover, we introduce a statistical feature extractor to utilize informative statistical information from the signals captured by Gabor filters, and a gate selection mechanism to enable efficient computation by only considering qualified regions as input for texture extraction. Through the integration of features from the Gabor-filter-based texture branch and CNN-based semantic branch, we achieve comprehensive information extraction. We demonstrate the efficacy of our method on multiple datasets, including CUB-200-2011, NA-bird, Stanford Dogs, and GTOS-mobile. State-of-the-art performance is achieved using our approach.