This paper provides a comprehensive survey of recent advances in deep learning-based generic object detection. The goal is to summarize the state-of-the-art in this field, covering detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. Over 300 research contributions are included, highlighting the progress made in the past five years. The survey focuses on the challenge of building general-purpose object detection systems that can detect a wide range of object categories with high accuracy and efficiency. Object detection is a fundamental problem in computer vision, aiming to identify and locate objects in images. It has applications in various fields, including robot vision, consumer electronics, security, autonomous driving, and augmented reality. Deep learning techniques, particularly convolutional neural networks (CNNs), have significantly improved the performance of object detection. The introduction of deep learning has led to remarkable breakthroughs, with the performance of object detection systems improving dramatically since 2012. The paper discusses the main challenges in generic object detection, including accuracy and efficiency. Accuracy is affected by intra-class variations and the large number of object categories. Efficiency is challenged by the need to process large numbers of object categories and locations in real-time. The paper also reviews the progress in the past two decades, highlighting the shift from handcrafted features to deep learning-based methods. The paper introduces a brief overview of deep learning, focusing on CNNs and their ability to learn complex feature representations. It discusses the key components of CNNs, including convolution, nonlinearity, and pooling. The paper also reviews the popular datasets used in object detection, such as PASCAL VOC, ImageNet, MS COCO, and Open Images. These datasets have played a crucial role in advancing the field of object detection. The paper evaluates the performance of object detection algorithms using metrics such as detection speed, precision, and recall. It also discusses the evaluation criteria for object detection, including the use of bounding boxes and the importance of accurate localization. The paper highlights the challenges in evaluating object detection systems, particularly in terms of accuracy and efficiency. The paper reviews the detection frameworks used in object detection, including region-based (two-stage) frameworks and one-stage frameworks. It discusses the key components of these frameworks, including region proposal generation, feature extraction, and classification. The paper also discusses the challenges in designing efficient and effective detection frameworks, including the need for shared computation and the use of deep learning techniques. The paper concludes by summarizing the main challenges and progress in the field of generic object detection, highlighting the importance of deep learning in achieving high accuracy and efficiency in object detection. The paper emphasizes the need for further research in this area, particularly in improving the accuracy and efficiency of object detection systems.This paper provides a comprehensive survey of recent advances in deep learning-based generic object detection. The goal is to summarize the state-of-the-art in this field, covering detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. Over 300 research contributions are included, highlighting the progress made in the past five years. The survey focuses on the challenge of building general-purpose object detection systems that can detect a wide range of object categories with high accuracy and efficiency. Object detection is a fundamental problem in computer vision, aiming to identify and locate objects in images. It has applications in various fields, including robot vision, consumer electronics, security, autonomous driving, and augmented reality. Deep learning techniques, particularly convolutional neural networks (CNNs), have significantly improved the performance of object detection. The introduction of deep learning has led to remarkable breakthroughs, with the performance of object detection systems improving dramatically since 2012. The paper discusses the main challenges in generic object detection, including accuracy and efficiency. Accuracy is affected by intra-class variations and the large number of object categories. Efficiency is challenged by the need to process large numbers of object categories and locations in real-time. The paper also reviews the progress in the past two decades, highlighting the shift from handcrafted features to deep learning-based methods. The paper introduces a brief overview of deep learning, focusing on CNNs and their ability to learn complex feature representations. It discusses the key components of CNNs, including convolution, nonlinearity, and pooling. The paper also reviews the popular datasets used in object detection, such as PASCAL VOC, ImageNet, MS COCO, and Open Images. These datasets have played a crucial role in advancing the field of object detection. The paper evaluates the performance of object detection algorithms using metrics such as detection speed, precision, and recall. It also discusses the evaluation criteria for object detection, including the use of bounding boxes and the importance of accurate localization. The paper highlights the challenges in evaluating object detection systems, particularly in terms of accuracy and efficiency. The paper reviews the detection frameworks used in object detection, including region-based (two-stage) frameworks and one-stage frameworks. It discusses the key components of these frameworks, including region proposal generation, feature extraction, and classification. The paper also discusses the challenges in designing efficient and effective detection frameworks, including the need for shared computation and the use of deep learning techniques. The paper concludes by summarizing the main challenges and progress in the field of generic object detection, highlighting the importance of deep learning in achieving high accuracy and efficiency in object detection. The paper emphasizes the need for further research in this area, particularly in improving the accuracy and efficiency of object detection systems.