Learning Granularity-Aware Convolutional Neural Network for Fine-Grained Visual Classification
This work addresses the challenge of distinguishing highly similar objects in fine-grained visual classification, which is important for applications like species identification or product categorization, and it is incremental as it builds on existing CNN-based methods.
The authors tackled the problem of fine-grained visual classification by proposing a Granularity-Aware Convolutional Neural Network (GA-CNN) that learns multi-granularity features to spot subtle differences, achieving state-of-the-art results on three benchmark datasets.
Locating discriminative parts plays a key role in fine-grained visual classification due to the high similarities between different objects. Recent works based on convolutional neural networks utilize the feature maps taken from the last convolutional layer to mine discriminative regions. However, the last convolutional layer tends to focus on the whole object due to the large receptive field, which leads to a reduced ability to spot the differences. To address this issue, we propose a novel Granularity-Aware Convolutional Neural Network (GA-CNN) that progressively explores discriminative features. Specifically, GA-CNN utilizes the differences of the receptive fields at different layers to learn multi-granularity features, and it exploits larger granularity information based on the smaller granularity information found at the previous stages. To further boost the performance, we introduce an object-attentive module that can effectively localize the object given a raw image. GA-CNN does not need bounding boxes/part annotations and can be trained end-to-end. Extensive experimental results show that our approach achieves state-of-the-art performances on three benchmark datasets.