• Corpus ID: 52183570

Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks

  title={Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks},
  author={Shivang Agarwal and Jean Ogier du Terrail and Fr{\'e}d{\'e}ric Jurie},
Object detection-the computer vision task dealing with detecting instances of objects of a certain class (e.g., 'car', 'plane', etc.) in images-attracted a lot of attention from the community during the last 5 years. This strong interest can be explained not only by the importance this task has for many applications but also by the phenomenal advances in this area since the arrival of deep convolutional neural networks (DCNN). This article reviews the recent literature on object detection with… 

Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments

This paper investigates the performance of current state-of-the-art generic object detection algorithms by benchmarking results on the three well-known challenging datasets and presents the first comprehensive overview of recent approaches that have tackled the problem of object detection in challenging environments.

Object Detection in 20 Years: A Survey

This paper extensively reviews 400+ papers of object detection in the light of its technical evolution, spanning over a quarter-century's time (from the 1990s to 2019), and makes an in-deep analysis of their challenges as well as technical improvements in recent years.

Exploiting Concepts of Instance Segmentation to Boost Detection in Challenging Environments

This paper exploits pixel-level information to improve detection under challenging situations and exploits the recently proposed hybrid task cascade network that works collaboratively with detection and segmentation heads at different cascade levels.

Object detection using YOLO: challenges, architectural successors, datasets and applications

A comprehensive review of single stage object detectors specially YOLOs, regression formulation, their architecture advancements, and performance statistics is presented.

Smart Detection Under Different Weather Conditions

Two-stage detection algorithms, faster R-CNN, were adopted as the basic structure for the detection network, evaluated under different weather conditions and show that the accuracy of the detector is affected differently under different conditions, and more complex environments result in greater inaccuracy.

Fast Region Proposal Learning for Object Detection for Robotics

A further boost in accuracy can be obtained by adapting, in addition, the regions candidate generation on the task at hand, and this method performs fast adaptation of the detector, by only re-training the classification layer.

Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark

Investigating Low Level Features in CNN for Traffic Sign Detection and Recognition

A new architecture is proposed that splits the detection and classification branches of a CNN based object detector and is able to improve the average precision of the detection results by 5% to 19% on public datasets.



A Survey of Modern Object Detection Literature using Deep Learning

A rigorous review of the strengths and weaknesses of each detector leads to the present state of the art in the SSD class of single step detectors and the Faster R-CNN class of two step detectors.

Object Detection With Deep Learning: A Review

This paper provides a review of deep learning-based object detection frameworks and focuses on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further.

DetNet: A Backbone network for Object Detection

State-of-the-art results have been obtained for both object detection and instance segmentation on the MSCOCO benchmark based on the DetNet~(4.8G FLOPs) backbone.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

UnitBox: An Advanced Object Detection Network

A novel Intersection over Union (IoU) loss function for bounding box prediction, which regresses the four bounds of a predicted box as a whole unit, and introduces the UnitBox, which performs accurate and efficient localization, shows robust to objects of varied shapes and scales, and converges fast.

Wide-residual-inception networks for real-time object detection

A wide-residual-inception (WR-Inception) network is proposed, which constructs the architecture based on a residual inception unit that captures objects of various sizes on the same feature map, as well as shallower and wider layers, compared to state-of-the-art networks like ResNets.

R-FCN: Object Detection via Region-based Fully Convolutional Networks

This work presents region-based, fully convolutional networks for accurate and efficient object detection, and proposes position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.

DeepID-Net: Deformable deep convolutional neural networks for object detection

The proposed approach improves the mean averaged precision obtained by RCNN, which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set.

Scalable Object Detection Using Deep Neural Networks

This work proposes a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest.

Object Detection from Video Tubelets with Convolutional Neural Networks

This work introduces a complete framework for the VID task based on still-image object detection and general object tracking, and proposes a temporal convolution network to incorporate temporal information to regularize the detection results and shows its effectiveness for the task.