A Deeper Look into Convolutions via Pruning

• URL: http://arxiv.org/abs/2102.02804v1
• Date: Thu, 4 Feb 2021 18:55:03 GMT
• Title: A Deeper Look into Convolutions via Pruning
• Authors: Ilke Cugu, Emre Akbas
• Abstract summary: Modern architectures contain a very small number of fully-connected layers, often at the end, after multiple layers of convolutions. Although this strategy already reduces the number of parameters, most of the convolutions can be eliminated as well, without suffering any loss in recognition performance. In this work, we use the matrix characteristics based on eigenvalues in addition to the classical weight-based importance assignment approach for pruning to shed light on the internal mechanisms of a widely used family of CNNs.
• Score: 9.89901717499058
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional neural networks (CNNs) are able to attain better visual recognition performance than fully connected neural networks despite having much less parameters due to their parameter sharing principle. Hence, modern architectures are designed to contain a very small number of fully-connected layers, often at the end, after multiple layers of convolutions. It is interesting to observe that we can replace large fully-connected layers with relatively small groups of tiny matrices applied on the entire image. Moreover, although this strategy already reduces the number of parameters, most of the convolutions can be eliminated as well, without suffering any loss in recognition performance. However, there is no solid recipe to detect this hidden subset of convolutional neurons that is responsible for the majority of the recognition work. Hence, in this work, we use the matrix characteristics based on eigenvalues in addition to the classical weight-based importance assignment approach for pruning to shed light on the internal mechanisms of a widely used family of CNNs, namely residual neural networks (ResNets), for the image classification problem using CIFAR-10, CIFAR-100 and Tiny ImageNet datasets.

Related papers

• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• GoogLe2Net: Going Transverse with Convolutions [0.0]
  We propose a novel CNN architecture called GoogLe2Net. It consists of residual feature-reutilization inceptions (ResFRI) or split residual feature-reutilization inceptions (Split-ResFRI) Our GoogLe2Net is able to reutilize information captured by foregoing groups of convolutional layers and express multi-scale features at a fine-grained level.
  arXiv  Detail & Related papers  (2023-01-01T15:16:10Z)
• Pushing the Efficiency Limit Using Structured Sparse Convolutions [82.31130122200578]
  We propose Structured Sparse Convolution (SSC), which leverages the inherent structure in images to reduce the parameters in the convolutional filter. We show that SSC is a generalization of commonly used layers (depthwise, groupwise and pointwise convolution) in efficient architectures'' Architectures based on SSC achieve state-of-the-art performance compared to baselines on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet classification benchmarks.
  arXiv  Detail & Related papers  (2022-10-23T18:37:22Z)
• CEC-CNN: A Consecutive Expansion-Contraction Convolutional Network for Very Small Resolution Medical Image Classification [0.8108972030676009]
  We introduce a new CNN architecture which preserves multi-scale features from deep, intermediate, and shallow layers. Using a dataset of very low resolution patches from Pancreatic Ductal Adenocarcinoma (PDAC) CT scans we demonstrate that our network can outperform current state of the art models.
  arXiv  Detail & Related papers  (2022-09-27T20:01:12Z)
• SAR Despeckling Using Overcomplete Convolutional Networks [53.99620005035804]
  despeckling is an important problem in remote sensing as speckle degrades SAR images. Recent studies show that convolutional neural networks(CNNs) outperform classical despeckling methods. This study employs an overcomplete CNN architecture to focus on learning low-level features by restricting the receptive field. We show that the proposed network improves despeckling performance compared to recent despeckling methods on synthetic and real SAR images.
  arXiv  Detail & Related papers  (2022-05-31T15:55:37Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Over-and-Under Complete Convolutional RNN for MRI Reconstruction [57.95363471940937]
  Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture. We propose an Over-and-Under Complete Convolu?tional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN) The proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.
  arXiv  Detail & Related papers  (2021-06-16T15:56:34Z)
• A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection [40.58864817923371]
  We propose a lightweight neural network to reduce the computational and spatial complexity. In the proposed network, we replace normal convolutional layers with bottleneck layers that keep the same number of channels between input and output. We verify our light-weighted neural network on four sets of bitemporal SAR images.
  arXiv  Detail & Related papers  (2020-05-29T04:01:32Z)
• When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks [57.0502745301132]
  We propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Our micro-dense block can be integrated with neural architecture search based models to boost their performance.
  arXiv  Detail & Related papers  (2020-04-19T08:34:52Z)
• Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection [21.48875255723581]
  A mixed-precision quantized neural network with progressively ecreasing bitwidth is proposed to improve the trade-off between accuracy and compression. Experiments on typical network architectures and benchmark datasets demonstrate that the proposed method could achieve better or comparable results.
  arXiv  Detail & Related papers  (2019-12-29T14:11:33Z)

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.