Channel Planting for Deep Neural Networks using Knowledge Distillation

• URL: http://arxiv.org/abs/2011.02390v1
• Date: Wed, 4 Nov 2020 16:29:59 GMT
• Title: Channel Planting for Deep Neural Networks using Knowledge Distillation
• Authors: Kakeru Mitsuno, Yuichiro Nomura and Takio Kurita
• Abstract summary: We present a novel incremental training algorithm for deep neural networks called planting. Our planting can search the optimal network architecture with smaller number of parameters for improving the network performance. We evaluate the effectiveness of the proposed method on different datasets such as CIFAR-10/100 and STL-10.
• Score: 3.0165431987188245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, deeper and wider neural networks have shown excellent performance in computer vision tasks, while their enormous amount of parameters results in increased computational cost and overfitting. Several methods have been proposed to compress the size of the networks without reducing network performance. Network pruning can reduce redundant and unnecessary parameters from a network. Knowledge distillation can transfer the knowledge of deeper and wider networks to smaller networks. The performance of the smaller network obtained by these methods is bounded by the predefined network. Neural architecture search has been proposed, which can search automatically the architecture of the networks to break the structure limitation. Also, there is a dynamic configuration method to train networks incrementally as sub-networks. In this paper, we present a novel incremental training algorithm for deep neural networks called planting. Our planting can search the optimal network architecture with smaller number of parameters for improving the network performance by augmenting channels incrementally to layers of the initial networks while keeping the earlier trained parameters fixed. Also, we propose using the knowledge distillation method for training the channels planted. By transferring the knowledge of deeper and wider networks, we can grow the networks effectively and efficiently. We evaluate the effectiveness of the proposed method on different datasets such as CIFAR-10/100 and STL-10. For the STL-10 dataset, we show that we are able to achieve comparable performance with only 7% parameters compared to the larger network and reduce the overfitting caused by a small amount of the data.

Related papers

• A Faster Approach to Spiking Deep Convolutional Neural Networks [0.0]
  Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. We propose a network structure based on previous work to improve network runtime and accuracy.
  arXiv  Detail & Related papers  (2022-10-31T16:13:15Z)
• Group Fisher Pruning for Practical Network Compression [58.25776612812883]
  We present a general channel pruning approach that can be applied to various complicated structures. We derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Our method can be used to prune any structures including those with coupled channels.
  arXiv  Detail & Related papers  (2021-08-02T08:21:44Z)
• Layer Folding: Neural Network Depth Reduction using Activation Linearization [0.0]
  Modern devices exhibit a high level of parallelism, but real-time latency is still highly dependent on networks' depth. We propose a method that learns whether non-linear activations can be removed, allowing to fold consecutive linear layers into one. We apply our method to networks pre-trained on CIFAR-10 and CIFAR-100 and find that they can all be transformed into shallower forms that share a similar depth.
  arXiv  Detail & Related papers  (2021-06-17T08:22:46Z)
• Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks [50.684661759340145]
  Firefly neural architecture descent is a general framework for progressively and dynamically growing neural networks. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures. In particular, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-02-17T04:47:18Z)
• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks [78.47459801017959]
  Sparsity can reduce the memory footprint of regular networks to fit mobile devices. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice.
  arXiv  Detail & Related papers  (2021-01-31T22:48:50Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Wasserstein Routed Capsule Networks [90.16542156512405]
  We propose a new parameter efficient capsule architecture, that is able to tackle complex tasks. We show that our network is able to substantially outperform other capsule approaches by over 1.2 % on CIFAR-10.
  arXiv  Detail & Related papers  (2020-07-22T14:38:05Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• Knapsack Pruning with Inner Distillation [11.04321604965426]
  We propose a novel pruning method that optimize the final accuracy of the pruned network. We prune the network channels while maintaining the high-level structure of the network. Our method leads to state-of-the-art pruning results on ImageNet, CIFAR-10 and CIFAR-100 using ResNet backbones.
  arXiv  Detail & Related papers  (2020-02-19T16:04:48Z)
• Differentiable Sparsification for Deep Neural Networks [0.0]
  We propose a fully differentiable sparsification method for deep neural networks. The proposed method can learn both the sparsified structure and weights of a network in an end-to-end manner. To the best of our knowledge, this is the first fully differentiable sparsification method.
  arXiv  Detail & Related papers  (2019-10-08T03:57:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.