Learning Gabor Texture Features for Fine-Grained Recognition

by   Lanyun Zhu, et al.

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.


page 3

page 8

page 13

page 15

page 17


Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

Few-shot fine-grained learning aims to classify a query image into one o...

Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition

Open-set image recognition is a challenging topic in computer vision. Mo...

CardioXNet: A Novel Lightweight CRNN Framework for Classifying Cardiovascular Diseases from Phonocardiogram Recordings

The alarmingly high mortality rate and increasing global prevalence of c...

ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator

Recently, several Vision Transformer (ViT) based methods have been propo...

Neighborhood Rank Order Coding for Robust Texture Analysis and Feature Extraction

Research into the visual cortex and general neural information processin...

Fine-Grained Visual Classification using Self Assessment Classifier

Extracting discriminative features plays a crucial role in the fine-grai...

When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters

Image filters are fast, lightweight and effective, which make these conv...

Please sign up or login with your details

Forgot password? Click here to reset