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.

翻译：提取和利用类别判别性特征对于细粒度识别至关重要。现有研究已证明应用深度卷积神经网络（CNN）能够挖掘区分相似类别的特征。然而，CNN存在频率偏差和局部细节信息丢失等问题，这限制了细粒度类别识别的性能。为解决这一挑战，我们提出了一种新颖的纹理分支作为CNN特征提取分支的补充。受Gabor滤波器能有效捕获多频率特征和详细局部信息的启发，我们创新性地将其作为强大的纹理特征提取器。我们通过实施多种设计来增强Gabor滤波器的有效性，包括对参数值施加约束以及开发确定最优参数的学习方法。此外，我们引入了统计特征提取器以利用Gabor滤波器捕获信号中的信息性统计特征，并设计了门控选择机制，仅将合格区域作为纹理提取的输入以实现高效计算。通过集成基于Gabor滤波器的纹理分支与基于CNN的语义分支的特征，我们实现了全面的信息提取。我们在多个数据集（包括CUB-200-2011、NA-bird、Stanford Dogs和GTOS-mobile）上验证了该方法的有效性，并取得了最先进的性能。