What Do We Understand About Convolutional Networks?
arXiv:1803.08834
Abstract
This document will review the most prominent proposals using multilayer convolutional architectures. Importantly, the various components of a typical convolutional network will be discussed through a review of different approaches that base their design decisions on biological findings and/or sound theoretical bases. In addition, the different attempts at understanding ConvNets via visualizations and empirical studies will be reviewed. The ultimate goal is to shed light on the role of each layer of processing involved in a ConvNet architecture, distill what we currently understand about ConvNets and highlight critical open problems.
References in corpus (33)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- ADADELTA: An Adaptive Learning Rate Method
- Two-Stream Convolutional Networks for Action Recognition in Videos
- An overview of gradient descent optimization algorithms
- Deep Residual Learning for Image Recognition
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Generative Adversarial Text to Image Synthesis
- Densely Connected Convolutional Networks
- Understanding Neural Networks Through Deep Visualization
- Going Deeper with Convolutions
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- Fully Convolutional Networks for Semantic Segmentation
- Object Detectors Emerge in Deep Scene CNNs
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Layer Normalization
- Spatiotemporal Residual Networks for Video Action Recognition
- Deformable Convolutional Networks
- Gabor Convolutional Networks
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Learning Deep Features for Discriminative Localization
- Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
- Understanding Deep Image Representations by Inverting Them
- Convolutional Clustering for Unsupervised Learning
- Analyzing the Performance of Multilayer Neural Networks for Object Recognition
- Semantic Image Inpainting with Deep Generative Models
- Oriented Response Networks
Cited by in corpus (9)
- A novel database of Children's Spontaneous Facial Expressions (LIRIS-CSE)
- Opening the black box of deep learning
- Deep learning analysis of polaritonic waves images
- An Extensive Review on Spectral Imaging in Biometric Systems: Challenges and Advancements
- FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions
- A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
- TUCaN: Progressively Teaching Colourisation to Capsules
- Collaboration among Image and Object Level Features for Image Colourisation
- Sequential image processing methods for improving semantic video segmentation algorithms