Towards Efficient Convolutional Network Models with Filter Distribution Templates
Not on the map. Why?
Abstract (arXiv)
Increasing number of filters in deeper layers when feature maps are decreased is a widely adopted pattern in convolutional network design. It can be found in classical CNN architectures and in automatic discovered models. Even CNS methods commonly explore a selection of multipliers derived from this pyramidal pattern. We defy this practice by introducing a small set of templates consisting of easy to implement, intuitive and aggressive variations of the original pyramidal distribution of filters in VGG and ResNet architectures. Experiments on CIFAR, CINIC10 and TinyImagenet datasets show that models produced by our templates, are more efficient in terms of fewer parameters and memory needs.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 17 Apr 2021.
Builds on
22 of 31 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2014Going Deeper with Convolutionscited by 4,231
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
- 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
- 2018Rethinking the Value of Network Pruningcited by 595
- 2020What is the State of Neural Network Pruning?cited by 578
10 more
- 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
- 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
- 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 253
- 2020Pruning Neural Networks at Initialization: Why are We Missing the Mark?cited by 181
- 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
- 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
- 2019Network Pruning via Transformable Architecture Searchcited by 80
- 2020AOWS: Adaptive and optimal network width search with latency constraintscited by 17
- 2020NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networkscited by 8
- 2018Smallify: Learning Network Size while Trainingcited by 4
Built on by
Citing papers per year: 2021: 1.
1 paper.