DeepAI AI Chat
Log In Sign Up

Feature Fusion for Online Mutual Knowledge Distillation

by   Jangho Kim, et al.
Seoul National University

We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated from parallel neural networks. Specifically, we train a number of parallel neural networks as sub-networks, then we combine the feature maps from each sub-network using a fusion module to create a more meaningful feature map. The fused feature map is passed into the fused classifier for overall classification. Unlike existing feature fusion methods, in our framework, an ensemble of sub-network classifiers transfers its knowledge to the fused classifier and then the fused classifier delivers its knowledge back to each sub-network, mutually teaching one another in an online-knowledge distillation manner. This mutually teaching system not only improves the performance of the fused classifier but also obtains performance gain in each sub-network. Moreover, our model is more beneficial because different types of network can be used for each sub-network. We have performed a variety of experiments on multiple datasets such as CIFAR-10, CIFAR-100 and ImageNet and proved that our method is more effective than other alternative methods in terms of performance of both sub-networks and the fused classifier.


Distilling a Powerful Student Model via Online Knowledge Distillation

Existing online knowledge distillation approaches either adopt the stude...

Multi scale Feature Extraction and Fusion for Online Knowledge Distillation

Online knowledge distillation conducts knowledge transfer among all stud...

Feature-map-level Online Adversarial Knowledge Distillation

Feature maps contain rich information about image intensity and spatial ...

An Ensemble of Knowledge Sharing Models for Dynamic Hand Gesture Recognition

The focus of this paper is dynamic gesture recognition in the context of...

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

Unlike the conventional Knowledge Distillation (KD), Self-KD allows a ne...

Similarity network fusion for scholarly journals

This paper explores intellectual and social proximity among scholarly jo...

Fusing restricted information

Information fusion deals with the integration and merging of data and in...