Learning Fine-grained Features via a CNN Tree for Large-scale Classification
This addresses the challenge of improving classification accuracy in large-scale datasets, though it appears incremental as it builds on existing CNN models.
The paper tackles the problem of enhancing discriminability in Convolutional Neural Networks for large-scale image classification by proposing a tree structure that progressively learns fine-grained features for subsets of classes, resulting in performance boosts for basic CNN models.
We propose a novel approach to enhance the discriminability of Convolutional Neural Networks (CNN). The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by learning features only among these classes. Such features are expected to be more discriminative, compared to features learned for all the classes. We develop a new algorithm to effectively learn the tree structure from a large number of classes. Experiments on large-scale image classification tasks demonstrate that our method could boost the performance of a given basic CNN model. Our method is quite general, hence it can potentially be used in combination with many other deep learning models.