# Deep Learning for Generic Object Detection: A Survey

**Authors:** Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, Matti Pietikäinen  
**arXiv:** [1809.02165](https://arxiv.org/abs/1809.02165)  
**Date:** 2018-09-06  
**Summary page:** https://www.summarizepaper.com/en/paper/1809.02165v4/

## Key points

- Deep learning techniques have revolutionized the field of computer vision
- Object detection is one of the most fundamental and challenging problems in this field
- Deep learning has led to remarkable breakthroughs in generic object detection
- The paper "Deep Learning for Generic Object Detection: A Survey" provides a comprehensive survey of recent achievements in this field brought about by deep learning techniques
- The survey includes more than 300 research contributions covering many aspects such as detection frameworks, object feature representation, object proposal generation, context modeling, training strategies and evaluation metrics
- The authors identify promising directions for future research in the field of generic object detection
- There is potential for further breakthroughs that could lead to significant improvements in real-world applications such as autonomous vehicles or surveillance systems
- This paper serves as an important resource for researchers seeking to stay up-to-date on the latest developments in this rapidly evolving field.

## Summary

The field of computer vision has been revolutionized by deep learning techniques, which have proven to be a powerful strategy for learning feature representations directly from data. One of the most fundamental and challenging problems in this field is object detection, which seeks to locate object instances from a large number of predefined categories in natural images. In recent years, deep learning has led to remarkable breakthroughs in generic object detection, making it an exciting area of research with rapid evolution. In their paper "Deep Learning for Generic Object Detection: A Survey," authors Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu and Matti Pietikäinen provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. The survey includes more than 300 research contributions covering many aspects such as detection frameworks, object feature representation, object proposal generation, context modeling, training strategies and evaluation metrics. The authors identify promising directions for future research in the field of generic object detection. With the help of deep learning techniques and advancements in computer vision technology there is potential for further breakthroughs that could lead to significant improvements in real-world applications such as autonomous vehicles or surveillance systems. This paper serves as an important resource for researchers seeking to stay up-to-date on the latest developments in this rapidly evolving field.