Attention Tree: Learning Hierarchies of Visual Features for Large-Scale Image Recognition
This work addresses the problem of computational efficiency in image classification for researchers and practitioners, though it appears incremental as it builds on existing tree-based methods.
The paper tackles the challenge of designing a computationally efficient multi-class classifier for large-scale image recognition by introducing Attention Tree (ATree), which uses recursive Adaboost training to construct a visual attention hierarchy, achieving accuracy improvement over state-of-the-art tree-based methods on Caltech-256 and SUN datasets at significantly lower computational cost.
One of the key challenges in machine learning is to design a computationally efficient multi-class classifier while maintaining the output accuracy and performance. In this paper, we present a tree-based classifier: Attention Tree (ATree) for large-scale image classification that uses recursive Adaboost training to construct a visual attention hierarchy. The proposed attention model is inspired from the biological 'selective tuning mechanism for cortical visual processing'. We exploit the inherent feature similarity across images in datasets to identify the input variability and use recursive optimization procedure, to determine data partitioning at each node, thereby, learning the attention hierarchy. A set of binary classifiers is organized on top of the learnt hierarchy to minimize the overall test-time complexity. The attention model maximizes the margins for the binary classifiers for optimal decision boundary modelling, leading to better performance at minimal complexity. The proposed framework has been evaluated on both Caltech-256 and SUN datasets and achieves accuracy improvement over state-of-the-art tree-based methods at significantly lower computational cost.