Feature Fusion for Online Mutual Knowledge Distillation
This work addresses the challenge of boosting accuracy in image classification tasks, offering a novel approach for researchers and practitioners, though it is incremental as it builds on existing feature fusion and knowledge distillation methods.
The paper tackles the problem of improving classifier performance by proposing Feature Fusion Learning (FFL), a framework that uses a fusion module to combine feature maps from parallel neural networks and enables mutual knowledge distillation between sub-networks and a fused classifier, resulting in enhanced performance for both on datasets like CIFAR-10, CIFAR-100, and ImageNet.
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.