SSD: Single Shot MultiBox Detector
@inproceedings{Liu2016SSDSS, title={SSD: Single Shot MultiBox Detector}, author={Wei Liu and Dragomir Anguelov and Dumitru Erhan and Christian Szegedy and Scott E. Reed and Cheng-Yang Fu and Alexander C. Berg}, booktitle={ECCV}, year={2016} }
We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default box and produces adjustments to the box to better match the object shape. Additionally, the network combines predictions from multiple… CONTINUE READING
Figures, Tables, and Topics from this paper.
Citations
Publications citing this paper.
SHOWING 1-10 OF 3,587 CITATIONS
A Preliminary Evaluation of Pedestrian Detection on Real-World Video Surveillance
VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED
BlitzNet: A Real-Time Deep Network for Scene Understanding
VIEW 17 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED
A Benchmarking of Learning Strategies for Pest Detection and Identification on Tomato Plants for Autonomous Scouting Robots Using Internal Databases
VIEW 12 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED
A Novel Effectively Optimized One-Stage Network for Object Detection in Remote Sensing Imagery
VIEW 10 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED
A Simple and Efficient Network for Small Target Detection
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED
A Unified Optimization Approach for CNN Model Inference on Integrated GPUs
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED
ACF Based Region Proposal Extraction for YOLOv3 Network Towards High-Performance Cyclist Detection in High Resolution Images
VIEW 13 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED
Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery
VIEW 13 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED
Automated detection of fundic gland polyps from endoscopic images using SSD
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED
Automatic analysis of crowd dynamics using computer vision and machine learning approaches
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED
FILTER CITATIONS BY YEAR
CITATION STATISTICS
1,020 Highly Influenced Citations
Averaged 1,169 Citations per year from 2017 through 2019