Unifying and Merging Well-trained Deep Neural Networks for Inference Stage

Abstract

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights. The shared weights are further re-trained to fine-tune the performance of the merged model. The proposed method effectively produces a compact model that may run original tasks simultaneously on resource-limited devices. As it preserves the general architectures and leverages the co-used weights of well-trained networks, a substantial training overhead can be reduced to shorten the system development time. Experimental results demonstrate a satisfactory performance and validate the effectiveness of the method.

arXiv commentTo appear in the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence, 2018. (IJCAI-ECAI 2018)

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Caffe: Convolutional Architecture for Fast Feature Embedding
• An Overview of Multi-Task Learning in Deep Neural Networks
• Pruning Filters for Efficient ConvNets
• Channel Pruning for Accelerating Very Deep Neural Networks
• Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Cited by in corpus (4)

• Collaborative Intelligence: Challenges and Opportunities
• Feature Partitioning for Efficient Multi-Task Architectures
• Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?
• Pruning-Aware Merging for Efficient Multitask Inference