DecomposeMe: Simplifying ConvNets for End-to-End Learning

Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community. However, these networks are computationally demanding and not suitable for embedded devices where memory and time consumption are relevant. In this paper, we propose DecomposeMe, a simple but effective technique to learn features using 1D convolutions. The proposed architecture enables both simplicity and filter sharing leading to increased learning capacity. A comprehensive set of large-scale experiments on ImageNet and Places2 demonstrates the ability of our method to improve performance while significantly reducing the number of parameters required. Notably, on Places2, we obtain an improvement in relative top-1 classification accuracy of 7.7\% with an architecture that requires 92% fewer parameters compared to VGG-B. The proposed network is also demonstrated to generalize to other tasks by converting existing networks.

• Publication year

  2016

• Venue

  arXiv.org

• Publication date

  2016-06-17

• Fields of study

  Computer Science

• Identifiers
  arXiv 1606.05426
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Sparse Convolutional Neural Networks

  2015cited by this paper
• Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

  2015influential reference
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

  2015cited by this paper
• Reducing Overfitting in Deep Networks by Decorrelating Representations

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Distilling the Knowledge in a Neural Network

  2015cited by this paper
• MatConvNet: Convolutional Neural Networks for MATLAB

  2014cited by this paper
• ImageNet Large Scale Visual Recognition Challenge

  2014influential reference
• One weird trick for parallelizing convolutional neural networks

  2014cited by this paper
• On the Number of Linear Regions of Deep Neural Networks

  2014cited by this paper
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation

  2014influential reference
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014influential reference
• Speeding up Convolutional Neural Networks with Low Rank Expansions

  2014cited by this paper
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

  2013cited by this paper
• Vision meets robotics: The KITTI dataset

  2013cited by this paper
• Predicting Parameters in Deep Learning

  2013cited by this paper
• Network In Network

  2013cited by this paper
• Learning Separable Filters

  2013cited by this paper
• Are we ready for autonomous driving? The KITTI vision benchmark suite

  2012cited by this paper
• Improving neural networks by preventing co-adaptation of feature detectors

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Practical Bayesian Optimization of Machine Learning Algorithms

  2012cited by this paper
• Torch7: A Matlab-like Environment for Machine Learning

  2011cited by this paper
• Understanding the difficulty of training deep feedforward neural networks

  2010cited by this paper
• ImageNet: A large-scale hierarchical image database

  2009cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper

• The DeepLabV3+ Algorithm Combined With the ResNeXt Network for Medical Image Segmentation

  2025cites this paper
• A Noise-Induced Hearing Loss Prediction Model Based on Asymmetric Convolution for Workers Exposed to Complex Industrial Noise

  2024cites this paper
• BiConvNet: Integrating Spatial Details and Deep Semantic Features in a Bilateral-Branch Image Segmentation Network

  2024cites this paper
• Research on building extraction from remote sensing imagery using efficient lightweight residual network

  2024cites this paper
• An Improved SAR Image Semantic Segmentation Deeplabv3+ Network Based on the Feature Post-Processing Module

  2023cites this paper
• SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognition

  2023cites this paper
• MUREN: MUltistage Recursive Enhanced Network for Coal-Fired Power Plant Detection

  2023cites this paper
• SARFB: Strengthened Asymmetric Receptive Field Block for Accurate Infrared Ship Detection

  2023cites this paper
• A lightweight convolutional neural network for pose estimation of a planar model

  2022cites this paper
• Analysis of segmentation performance of U-shape neural network algorithm by multi-type encoders for pavement cracks

  2022cites this paper
• Fully Decoupled Residual ConvNet for Real-Time Railway Scene Parsing of UAV Aerial Images

  2022cites this paper
• Deep Learning Based Real-Time Semantic Segmentation of Cerebral Vessels and Cranial Nerves in Microvascular Decompression Scenes

  2022cites this paper
• Real-time segmentation method of billet infrared image based on multi-scale feature fusion

  2022cites this paper
• Lane Line Detection based on Parallel Spatial Separation Convolution

  2021cites this paper
• Context Based Emotion Recognition Using EMOTIC Dataset

  2020cites this paper
• MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications

  2020cites this paper
• Building NAS: Automatic designation of efficient neural architectures for building extraction in high-resolution aerial images

  2020cites this paper
• Teeth Detection and Dental Problem Classification in Panoramic X-Ray Images using Deep Learning and Image Processing Techniques

  2020cites this paper
• A Lightweight and Efficient Network for Logistics Truck Scene Semantic Segmentation

  2020cites this paper
• The Fusion Knowledge of Face, Body and Context for Emotion Recognition

  2019cites this paper
• ESFNet: Efficient Network for Building Extraction From High-Resolution Aerial Images

  2019cites this paper
• Training Efficient Semantic Segmentation CNNs on Multiple Datasets

  2019cites this paper
• Fast Portrait Segmentation with extremely light-weight network

  2019cites this paper
• Fast and Light-weight Portrait Segmentation

  2019cites this paper
• Exploiting the Redundancy in Convolutional Filters for Parameter Reduction

  2019cites this paper
• Spatial Sampling Network for Fast Scene Understanding

  2019cites this paper
• Comparing Optimization Methods of Neural Networks for Real-time Inference

  2019cites this paper
• Fast Portrait Segmentation With Highly Light-Weight Network

  2019cites this paper
• ARC-Net: An Efficient Network for Building Extraction From High-Resolution Aerial Images

  2019cites this paper
• A Novel 1D-Convolution Accelerator for Low-Power Real-time CNN processing on the Edge

  2018cites this paper
• Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision

  2018cites this paper
• Restricted Deformable Convolution-Based Road Scene Semantic Segmentation Using Surround View Cameras

  2018cites this paper
• ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation

  2018influential citation
• Unifying Terrain Awareness for the Visually Impaired through Real-Time Semantic Segmentation

  2018influential citation
• Binarized Convolutional Neural Networks for Efficient Inference on GPUs

  2018cites this paper
• Class-Weighted Convolutional Features for Visual Instance Search

  2017cites this paper
• Faster Convolutional Neural Networks

  2017cites this paper
• Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration

  2017cites this paper
• Compressing deep neural networks for efficient visual inference

  2017cites this paper
• Compression-aware Training of Deep Networks

  2017influential citation
• Deep Learning for Mobile Multimedia

  2017cites this paper
• The Devil is in the Decoder: Classification, Regression and GANs

  2017cites this paper
• Efficient ConvNet for real-time semantic segmentation

  2017cites this paper
• Emotion Recognition in Context

  2017cites this paper
• Domain-Adaptive Deep Network Compression

  2017cites this paper
• Compression of convolutional neural networks using Tucker Decomposition

  2017cites this paper
• Class Weighted Convolutional Features for Image Retrieval

  2017cites this paper
• Learning the Number of Neurons in Deep Networks

  2016cites this paper