Fine-grained image classification is quite challenging due to high inter-class similarity and large intra-class variations. Another issue is the small amount of training images with a large number of classes to be identified. To address the chal-lenges, we propose a model for fine-grained image classifi-cation with its application to bird species recognition. Based on the features extracted by bilinear convolutional neural network (BCNN), we propose an on-line dictionary learn-ing algorithm where the principle of sparsity is integrated into classification. The features extracted by BCNN encode pairwise neuron interaction in a translation-invariant manner. This property is valuable to fine-grained classification. The proposed algorithm for dictionary learning further carries out sparsity based classification, where training data can be rep-resented with a less number of dictionary atoms. It alleviates the problems caused by insufficient training data, and makes classification much more efficient. Our approach is evaluated and compared with the state-of-the-art approaches on the CUB-200-2011 dataset. The promising experimental results demonstrate its efficacy and superiority.
|Name||Proceedings - International Conference on Image Processing, ICIP|
- Deep learning
- Fine-grained image classification
- On-line dictionary learning
- Sparse representation