MatConvNet - Convolutional Neural Networks for MATLAB

2014/12/15 by Andrea Vedaldi, Karel Lenc, Vedaldi, Andrea +1 · 21 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Neural Network Applications #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Mathematical Software (cs.MS) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.LG #cs.MS #cs.NE

paper · pdf · doi:10.48550/arxiv.1412.4564

Updated for release v1.0-beta20

openalex publication_date 2014/12/15 · arxiv created 2016/05/05 · arxiv updated 2016/05/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

MatConvNet is an implementation of Convolutional Neural Networks (CNNs) for MATLAB. The toolbox is designed with an emphasis on simplicity and flexibility. It exposes the building blocks of CNNs as easy-to-use MATLAB functions, providing routines for computing linear convolutions with filter banks, feature pooling, and many more. In this manner, MatConvNet allows fast prototyping of new CNN architectures; at the same time, it supports efficient computation on CPU and GPU allowing to train complex models on large datasets such as ImageNet ILSVRC. This document provides an overview of CNNs and how they are implemented in MatConvNet and gives the technical details of each computational block in the toolbox.

Citations

• ImageNet classification with deep convolutional neural networks
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Cited by

• Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
• Exploring Diffusion with Test-Time Training on Efficient Image Restoration
• Deeply-Recursive Convolutional Network for Image Super-Resolution
• Seeing into Darkness: Scotopic Visual Recognition
• Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution
• Efficient piecewise training of deep structured models for semantic segmentation
• Deep Semantic Face Deblurring
• Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
• When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
• Discriminative Label Consistent Domain Adaptation
• Learning a Discriminative Prior for Blind Image Deblurring
• End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth\n Data
• Synthesizing Dynamic Patterns by Spatial-Temporal Generative ConvNet
• 3D Morphable Models as Spatial Transformer Networks
• A Discriminatively Learned CNN Embedding for Person Reidentification
• VoxCeleb2: Deep Speaker Recognition
• Understanding trained CNNs by indexing neuron selectivity
• Self-Supervised Video Representation Learning With Odd-One-Out Networks
• Accelerating Deep Learning with Shrinkage and Recall
• Deep Learning for Visual Tracking: A Comprehensive Survey
• Deformable Object Tracking With Gated Fusion

Related

• DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
• Convolutional Neural Networks:
• An Introduction to Convolutional Neural Networks
• SdcNet: A Computation-Efficient CNN for Object Recognition
• LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning