Network of Experts for Large-Scale Image Categorization

Abstract

We present a tree-structured network architecture for large scale image classification. The trunk of the network contains convolutional layers optimized over all classes. At a given depth, the trunk splits into separate branches, each dedicated to discriminate a different subset of classes. Each branch acts as an expert classifying a set of categories that are difficult to tell apart, while the trunk provides common knowledge to all experts in the form of shared features. The training of our "network of experts" is completely end-to-end: the partition of categories into disjoint subsets is learned simultaneously with the parameters of the network trunk and the experts are trained jointly by minimizing a single learning objective over all classes. The proposed structure can be built from any existing convolutional neural network (CNN). We demonstrate its generality by adapting 4 popular CNNs for image categorization into the form of networks of experts. Our experiments on CIFAR100 and ImageNet show that in every case our method yields a substantial improvement in accuracy over the base CNN, and gives the best result achieved so far on CIFAR100. Finally, the improvement in accuracy comes at little additional cost: compared to the base network, the training time is only moderately increased and the number of parameters is comparable or in some cases even lower.

ECCV 2016

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Improving neural networks by preventing co-adaptation of feature detectors
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Scalable Bayesian Optimization Using Deep Neural Networks
• Balanced k-Means and Min-Cut Clustering

Cited by in corpus (10)

• Multi-Level Factorisation Net for Person Re-Identification
• NBDT: Neural-Backed Decision Trees
• Towards Good Practices for Deep 3D Hand Pose Estimation
• Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
• Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
• SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
• Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
• Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning
• SECS: Efficient Deep Stream Processing via Class Skew Dichotomy
• SONG: Self-Organizing Neural Graphs