Recent Advances in Deep Learning for Object Detection

  title={Recent Advances in Deep Learning for Object Detection},
  author={Xiongwei Wu and Doyen Sahoo and Steven C. H. Hoi},

Object Detection using Deep Learning: A Review

A completely deep learning-based approach is used to solve the problems of object detection in an end to end fashion using wireless sensor network with the goal of obtain high accuracy with a real time performance.

Att-FPA: Boosting Feature Perceive for Object Detection

A novel method called Attentional Feature Perceive and Augmentation (Att-FPA) is constructed, which establishes a new efficient method of feature representation, which outperforms the state-of-the-art models in object detection.

Toward Detection of Small Objects Using Deep Learning Methods: A Review

Implementing several techniques to improve object detection performance, particularly for small object detection, from three perspectives: network improvement, input data optimization, and dataset enhancement (data augmentation, creating own dataset).

Tools, techniques, datasets and application areas for object detection in an image: a review

A systematic review has been followed to summarize the current research work’s findings and discuss seven research questions related to object detection.

Object Detection by a Hybrid of Feature Pyramid and Deep Neural Networks

It can be concluded that using deep learning algorithms and CNNs and combining them with a feature network can significantly enhance object detection precision.

A Study on Object Detection Using Convolutional Neural Networks and Various Pretrained Models

Various state of the art deep learning algorithms i.e., VGG-16, VGG19, DenseNet-121, InceptionV3 and customized 3 layers CNN model for object detection are presented.

A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets

This survey paper specially analyzed computer vision-based object detection challenges and solutions by different techniques and showed future directions with existing challenges of the field.

Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses

This paper proposes to explore and overcome problem of class-imbalance in general machine learning by application of several weighted variants of Cross Entropy loss, for examples Balanced CrossEntropy, Focal Loss and Class-Balanced Loss Based on Effective Number of Samples to the authors' object detector.

Object Localization in Weakly Labeled Remote Sensing Images Based on Deep Convolutional Features

The core idea of the method is to recognize multiple objects in an image using only image-level semantic labels and indicate the recognized objects with location points instead of box extent and outperforms the-state-of-the-art methods.



Deep Learning for Generic Object Detection: A Survey

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.

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.

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

This article reviews the recent literature on object detection with deep CNN, in a comprehensive way, and provides an in-depth view of these recent advances.

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.

Deep Regionlets for Object Detection

This paper proposes a "region selection network" and a "gating network" that serves as a guidance on where to select regions to learn the features from in Regionlet and achieves comparable state-of-the-art results.

Deep feature based contextual model for object detection

Learning to Segment Object Candidates

A new way to generate object proposals is proposed, introducing an approach based on a discriminative convolutional network that obtains substantially higher object recall using fewer proposals and is able to generalize to unseen categories it has not seen during training.

Accurate Face Detection for High Performance

This report applies the Intersection over Union (IoU) loss function for regression, employ the two-step classification and regression for detection, revisit the data augmentation based on data-anchor-sampling for training, utilize the max-out operation for classification and use the multi-scale testing strategy for inference.

Multi-scale Location-Aware Kernel Representation for Object Detection

This paper proposes a novel Multi-scale Location-aware Kernel Representation (MLKP) to capture high-order statistics of deep features in proposals, which achieves very competitive performance with state-of-the-art methods, and improves Faster R-CNN by 4.9%, 4.7% and 5.0% respectively.

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.