Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey

By Junwei Han, Dingwen Zhang, Gong Cheng, Nian Liu, Dong Xu. 2018

597 citations recorded by the source corpus.

Object detection, including objectness detection (OD), salient object detection (SOD), and category-specific object detection (COD), is one of the most fundamental yet challenging problems in the computer vision community. Over the last several decades, great efforts have been made by researchers to tackle this problem, due to its broad range of applications for other computer vision tasks such as activity or event recognition, content-based image retrieval and scene understanding, etc. While numerous methods have been presented in recent years, a comprehensive review for the proposed high-quality object detection techniques, especially for those based on advanced deep-learning techniques, is still lacking. To this end, this article delves into the recent progress in this research field, including 1) definitions, motivations, and tasks of each subdirection; 2) modern techniques and essential research trends; 3) benchmark data sets and evaluation metrics; and 4) comparisons and analysis of the experimental results. More importantly, we will reveal the underlying relationship among OD, SOD, and COD and discuss in detail some open questions as well as point out several unsolved challenges and promising future works.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

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

In Human-Computer Interaction

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, neutral): “[305, 306, 307, 308, 309] and the code repositories https://github.”
Deep Learning for Unmanned Aerial Vehicle-Based Object Detection and Tracking: A survey (2021, background): “CONTRIBUTION Up to now, reviews concerning object detection and tracking from airborne and spaceborne data sets can be found [34], [35].”
From Discriminant to Complete: Reinforcement Searching-Agent Learning for Weakly Supervised Object Detection (2020, methodology): “In future works, we will explore the potential of using the saliency detection technique [1], [58], [59] to obtain the better local discriminative regions and apply the more advanced reinforcement learning algorithms [60], [61] to further improve the learning performance of the proposed WSOD framewo”
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (2018, background): “* Corresponding author contexts and the difficulty in exploring saliency-specific prior knowledge, a large body of deep convolutional neural networks (CNNs) [11-17] have been designed for RGB-induced salient object detection and have achieved appealing performance.”
DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection (2019, background): “Generally, there are two main categories of CNN-based object detection approaches: the object proposal-based approaches and the regression-based approaches [8].”
CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection (2020, unknown): “Several CNN models such as GoogLeNet [22], VGG-Net [23], ResNet [24], and AlexNet [25] are popular at image classification in the last decade.”
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation (2020, background): “O BJECT detection and instance segmentation have received overwhelming research attention due to their practical applications in video surveillance, visual tracking, face detection and inverse synthetic aperture radar detection [1]–[6].”
Convolutional neural network: a review of models, methodologies and applications to object detection (2019, unknown): “Junwei Han [69] 2018 SOD (CNN based), COCO PASCAL VOC, MS COD Obtains a mAP of 78.”
Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark (2019, background): “…learning based object detection approaches have achieved great success in natural scene images (Agarwal et al., 2018; Dai et al., 2016; Girshick, 2015; Girshick et al., 2014; Han et al., 2018; Liu et al., 2018a; Liu et al., 2016a; Redmon et al., 2016; Redmon and Farhadi, 2017; Ren et al., 2017).”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, background): “[46] look into the sub-directions of object detection, and conclude the recent progress in object-ness detection, SOD, and category-speciﬁc object detection (COD).”
Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “Therefore we also encourage readers to refer to recent surveys on object detection methods (Han et al., 2018; Liu et al., 2018a).”