A Taxonomy of Deep Convolutional Neural Nets for Computer Vision

TL;DR

This paper provides a comprehensive taxonomy and survey of convolutional neural network architectures tailored for computer vision, highlighting their evolution, variations, and suitability for different tasks to guide practitioners.

Contribution

It offers a structured taxonomy of CNN architectures for computer vision, filling the gap of a dedicated survey and aiding practitioners in selecting appropriate models.

Findings

Analyzes the evolution of CNN architectures from AlexNet onwards.

Classifies CNN variations based on their design and application.

Serves as a practical guide for novice practitioners in deep learning for vision.

Abstract

Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative -- that of automatically learning problem-specific features. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. Although general surveys of this fast-moving paradigm (i.e. deep-networks) exist, a survey specific to computer vision is missing. We specifically consider one form of deep networks widely used in computer vision - convolutional neural networks (CNNs). We start with "AlexNet" as our base CNN and then examine the broad variations proposed over time to suit different applications. We hope that our recipe-style survey will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision.