Deep Learning for Generic Object Detection: A Survey (2018-09-06T00:00:00.000000Z)

TL;DR

A comprehensive survey of the recent achievements in this field brought about by deep learning techniques, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics.

Abstract

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

Authors

Xiaogang Wang

21 papers

P. Fieguth

5 papers

Li Liu

3 papers

TL;DR

Abstract

Authors

References375 items

Switchable Normalization for Learning-to-Normalize Deep Representation

CenterNet: Keypoint Triplets for Object Detection

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

Towards Universal Object Detection by Domain Attention

High-Resolution Representations for Labeling Pixels and Regions

DetNAS: Neural Architecture Search on Object Detection

Deep High-Resolution Representation Learning for Human Pose Estimation

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

WIDER Face and Pedestrian Challenge 2018: Methods and Results

Hybrid Task Cascade for Instance Segmentation

FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction

Scale-Aware Trident Networks for Object Detection

Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection

Graph Neural Networks: A Review of Methods and Applications

Few-Shot Object Detection via Feature Reweighting

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

Graph-Based Global Reasoning Networks

Polarity Loss for Zero-shot Object Detection

Gradient Harmonized Single-stage Detector

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

The Open Images Dataset V4

Automated Machine Learning: From Principles to Practices

Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection

Bounding Box Regression With Uncertainty for Accurate Object Detection

A Survey on Deep Learning

DetNet: Design Backbone for Object Detection

Towards Understanding Regularization in Batch Normalization

Deep Feature Pyramid Reconfiguration for Object Detection

SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection

CornerNet: Detecting Objects as Paired Keypoints

Acquisition of Localization Confidence for Accurate Object Detection

Modeling Visual Context is Key to Augmenting Object Detection Datasets

End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection

RepMet: Representative-based metric learning for classification and one-shot object detection

Path-Level Network Transformation for Efficient Architecture Search

Places: A 10 Million Image Database for Scene Recognition

Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships

Scale-Transferrable Object Detection

Occluded Pedestrian Detection Through Guided Attention in CNNs

Quantization Mimic: Towards Very Tiny CNN for Object Detection

Zero-Shot Object Detection by Hybrid Region Embedding

DetNet: A Backbone network for Object Detection

Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

Zero-Shot Object Detection

Multi-scale Location-Aware Kernel Representation for Object Detection

Efficient Parametrization of Multi-domain Deep Neural Networks

Group Normalization

Revisiting RCNN: On Awakening the Classification Power of Faster RCNN

Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts

An End-to-End TextSpotter with Explicit Alignment and Attention

Path Aggregation Network for Instance Segmentation

LSTD: A Low-Shot Transfer Detector for Object Detection

Meta-Learning for Semi-Supervised Few-Shot Classification

Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges

Approximate Communication

Panoptic Segmentation

R-FCN-3000 at 30fps: Decoupling Detection and Classification

Learning Efficient Object Detection Models with Knowledge Distillation

Cascade R-CNN: Delving Into High Quality Object Detection

Progressive Neural Architecture Search

Single-Shot Object Detection with Enriched Semantics

Relation Networks for Object Detection

Towards Accurate Binary Convolutional Neural Network

Learning to Segment Every Thing

DOTA: A Large-Scale Dataset for Object Detection in Aerial Images

CondenseNet: An Efficient DenseNet Using Learned Group Convolutions

An Analysis of Scale Invariance in Object Detection - SNIP

Frustum PointNets for 3D Object Detection from RGB-D Data

Receptive Field Block Net for Accurate and Fast Object Detection

MegDet: A Large Mini-Batch Object Detector

Light-Head R-CNN: In Defense of Two-Stage Object Detector

Single-Shot Refinement Neural Network for Object Detection

NISP: Pruning Networks Using Neuron Importance Score Propagation

Improving Object Localization with Fitness NMS and Bounded IoU Loss

Detect to Track and Track to Detect

Deep learning in remote sensing: a review