CVAug 22, 2018

A Survey of Modern Object Detection Literature using Deep Learning

arXiv:1808.07256v18 citations
Originality Synthesis-oriented
AI Analysis

It provides a systematic review for researchers and practitioners in computer vision, but is incremental as a survey paper.

This paper conducts a comprehensive survey of modern object detection algorithms using deep learning, focusing on SSD and Faster R-CNN classes, and reviews their strengths and weaknesses to present the current state of the art.

Object detection is the identification of an object in the image along with its localisation and classification. It has wide spread applications and is a critical component for vision based software systems. This paper seeks to perform a rigorous survey of modern object detection algorithms that use deep learning. As part of the survey, the topics explored include various algorithms, quality metrics, speed/size trade offs and training methodologies. This paper focuses on the two types of object detection algorithms- the SSD class of single step detectors and the Faster R-CNN class of two step detectors. Techniques to construct detectors that are portable and fast on low powered devices are also addressed by exploring new lightweight convolutional base architectures. Ultimately, a rigorous review of the strengths and weaknesses of each detector leads us to the present state of the art.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes