Object Detection With Deep Learning: A Review

By Zhong-Qiu Zhao, Shou-tao Xu, Xindong Wu. 2018

4,776 citations recorded by the source corpus.

Due to object detection’s close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Real-World Image Datasets for Federated Learning (2019, methodology): “With the rapid development of deep learning, object detection algorithms have been greatly improved in the past few decades [ Ren et al. , 2017; Redmon and Farhadi, 2018a; Zhao et al. , 2018 ] .”
AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training (2021, background): “Recently, deep neural networks (DNNs) became the dominant paradigm in various real-world applications, for example, image classiﬁcation [12, 18, 17, 16, 19], semantic segmentation [43, 32, 27], object detection [39, 15, 38, 46, 35].”
Unsupervised Domain Adaptation of Object Detectors: A Survey (2021, background): “There are a variety of surveys [87], [88], [89] on the topic covering wide range of techniques proposed over the past decade for object detection.”
Probabilistic Knowledge Transfer for Lightweight Deep Representation Learning (2020, background): “D EEP learning (DL) allowed for tackling many difﬁcult problems with great success [1], ranging from challenging computer vision problems [2] to complex reinforcement learning problems [3].”
Object Detection in 20 Years: A Survey (2019, neutral): “SPPNet [17], Fast RCNN [18], Faster RCNN [19], YOLO [20], [21], [22], SSD [23], FPN [24], Retina-Net [25], CornerNet [26], CenterNet [27], and”
A survey of deep learning techniques for autonomous driving (2019, background): “Although great progress has been reported with respect to accuracy in object detection and recognition [173], current systems are mainly designed to calculate 2D or 3D bounding boxes for a couple of trained object classes, or to provide a segmented image of the driving environment.”
Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, background): “Attention has been the center of significant research efforts over the past few years, and image attention has been flourishing in many different machine learning and vision applications, for example, classification [179], detection [198], image captioning [61], 3D analysis [145, 49], etc.”
Thin MobileNet: An Enhanced MobileNet Architecture (2019, background): “In realtime applications such as image classification [8], captioning [9], object detection [10,23,33] and semantic segmentation [34] in autonomous driving, the inference time and accuracy are very important factors to one's safety.”
The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis (2020, background): “…the benefit of automatically learning high-level useful features directly without having to extract handcrafted features, and has a hierarchical feature representation, allowing these multilevel representations from a pixel to high-level semantic features which are learned automatically [3,4].”
A Survey of Visual Transformers (2021, methodology): “1) The Original Detectors: DEtection with TRansformer (DETR) [30] is the first end-to-end Transformer detector that eliminates hand-designed representations [181]–[184] and non-maximum suppression (NMS) post-processing, which redefines the object detection as a set prediction problem.”
YOLO v3-Tiny: Object Detection and Recognition using one stage improved model (2020, methodology): “Therefore its speed is quite good in contrast to RCNN [15].”
Artificial intelligence in the creative industries: a review (2020, background): “erent objects in a image or a video giving their bounding boxes, classes and pixel-level masks, as demonstrated in [169]. An in-depth review of object recognition using deep learning can be found in [273] and [184]. YOLO and its variants represent the current state-of-the-art in real-time object det”
FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters (2021, neutral): “are applied to maritime object detection directly or with modification to increase the model’s real-time performance and detection accuracy [34, 57, 56].”