Deep Learning for Generic Object Detection: A Survey

By Li Liu, Wanli Ouyang, Xiaogang Wang, Paul W. Fieguth, Jie Chen, Xinwang Liu, Matti Pietikäinen. 2018

2,829 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

AI and the Everything in the Whole Wide World Benchmark (2021, background): “…visual object recognition framed as the ability to recognize a sizable breadth of objects in a manner that rivals human capabilities [Liu et al., 2020], we observe ImageNet’s sheer size — both in terms of number of categories and number of images per category — further informs its…”
Deformable DETR: Deformable Transformers for End-to-End Object Detection (2020, background): “Modern object detectors employ many hand-crafted components (Liu et al., 2020), e.g., anchor generation, rule-based training target assignment, non-maximum suppression (NMS) post-processing.”
A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, background): “There exists a number of extensive surveys on general image-based object detection [133]–[135].”
Deep learning based brain tumor segmentation: a survey (2020, background): “Deep learning for generic object detection: A survey [22] arXiv 2018 A comprehensive review on deep learning based object detection Deep learning [23] Nature 2015 An introduction review on deep learning and its applications Recent advances in convolutional neural networks [24] PR 2015 A survey on co”
Deep semantic segmentation of natural and medical images: a review (2019, neutral): “Auto-DeepLab (Liu et al. (2019a)) Architecture”
Camouflaged Object Segmentation with Distraction Mining (2021, background): “Generic Object Detection (GOD) seeks to locate object instances from several predefined generic categories in natural images [31], which is one of the most fundamental and challenging problems in computer vision and forms the basis for solving complex or high-level vision tasks such as segmentation ”
Rearrangement: A Challenge for Embodied AI (2020, background): “Evaluation of the agent’s performance on subtasks such as object detection [48], rigid object state estimation and tracking [78], and localization [27] of the agent relative to objects connects with a breadth of research problems in the vision community.”
PP-YOLO: An Effective and Efficient Implementation of Object Detector (2020, background): “It mainly includes two branches: one-stage detectors and two-stage detectors[24].”
SwinIR: Image Restoration Using Swin Transformer (2021, methodology): “When used in vision problems such as image classification [66, 19, 84, 56, 45, 55, 75], object detection [6, 53, 74, 56], segmentation [84, 99, 56, 4] and crowd counting [47, 69], it learns to attend to important image regions by exploring the global interactions between different regions.”
Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges (2019, methodology): “segmentation, we refer the interested reader to the review papers [11], [12].”
Object detection using YOLO: challenges, architectural successors, datasets and applications (2022, background): “Due to the exponential increase of generated data from various sources, it has become a tedious and labor-intensive task to annotate each and every object in the visual contents [45, 73, 80].”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “A full review of these networks is beyond the scope of this paper, and we refer readers to the original papers [84, 87, 103, 214, 220] and to excellent surveys [15, 31, 75, 112, 133] for additional details.”
FoveaBox: Beyond Anchor-based Object Detector (2019, background): “Most state-of-the-art detectors rely on anchor boxes to enumerate the possible locations, scales, and aspect ratios for target objects [30].”
Camouflaged Object Detection (2020, background): “(a) Image (b) Generic object (c) Salient object (d) Camouflaged object Figure 2: Given an input image (a), we present the ground-truth for (b) panoptic segmentation [30] (which detects generic objects [39,44] including stuff and things), (c) salient instance/object detection [16, 33, 61, 76] (which ”
Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving (2019, background): “In recent years, with the development of technologies in computer vision and deep learning [12, 34, 36], numerous impressive methods are proposed for accurate 2D object detection [9, 8, 11, 32, 17, 24, 41, 18].”