SSD: Single Shot MultiBox Detector

@inproceedings{Liu2016SSDSS,
  title={SSD: Single Shot MultiBox Detector},
  author={W. Liu and Dragomir Anguelov and D. 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. [...] Key Method 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 feature maps with different resolutions to naturally handle objects of various sizes.Expand
View PDF on arXiv
12,782 Citations
Highly Influential Citations
2,301
Background Citations
4,002
Methods Citations
5,068
Results Citations
136

Supplemental Content

36:01
Video
PR-132: SSD: Single Shot MultiBox Detector
JinWon Lee
6 January 2019
Github Repo
Via Papers with Code
ChunML/ssd-tf2
A super clean implementation of SSD (Single Shot MultiBox Detector) made possible by Tensorflow 2.0
78 Stars • 35 Forks

12,782 Citations

Citation Type

Citation Type

Intelligent lighting system using single shot multibox detector
Single Shot MultiBox Detector is a single shot detector (uses a single shot) for multiple categories, which is faster than the latest generation such as YOLO (You only look once) and significantly… Expand
CDSSD: Refreshing Single Shot Object Detection Using a Conv-Deconv Network
TLDR
The framework, Conv-Deconv SSD (CDSSD), with its two key contributions – unsupervised pretraining and multi-layer confluence of convolution-deconvolution feature maps – results in state-of-the-art performance while utilizing significantly less number of bounding boxes and improved identification of small objects. Expand
Extend the shallow part of single shot multibox detector via convolutional neural network
TLDR
This paper proposes a single stage end-to-end image detection model called ESSD which can reach 79.4% mAP, which is higher than DSSD and SSD by 0.8 and 1.9 points respectively. Expand
Learning an Object Detector Using Zoomed Object Regions
TLDR
A novel training scheme is proposed to enhance the performance of the single shot multi-box detector by generating additional GT boxes by zooming in to and out from the original GT boxes to improve the semantic level of the feature map. Expand
Multi-scales feature integration single shot multi-box detector on small object detection
TLDR
An enhanced SSD with feature integrated modules which can improve the performance significantly over SSD, and outperforms a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed. Expand
Contrastive Relevance Propagation for Interpreting Predictions by a Single-Shot Object Detector
TLDR
This paper proposes Contrastive Relevance Propagation (CRP), an extension of Layer-wise Relevances Propagations (LRP) tailored for SSD that can consistently deal with SSD’s heterogeneous output, and create a heatmap that highlights a crucial part of the input, which is not available with a standard use of LRP. Expand
Detecting Small Objects in Thermal Images Using Single-Shot Detector
TLDR
DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection, outperforming a lot of state-of theart object detection algorithms in both aspects of accuracy and speed. Expand
Single Multi-feature detector for Amodal 3D Object Detection in RGB-D Images
TLDR
This paper proposes a single end-to-end framework based on the deep neural networks which hierarchically incorporates appearance and geometric features from 2.5D representation to 3D objects for fast and high-accuracy amodal 3D object detections in RGB-D images. Expand
CSSD: An End-to-End Deep Neural Network Approach to Pedestrian Detection
TLDR
A one-stage approach to compose a single deep neural network for pedestrian detection task in real-time and addresses the typical difficulty of detecting different scale pedestrian at only one layer by providing a novel channel fusion. Expand
Deep active learning for object detection
TLDR
A novel active learning method is developed which poses the layered architecture used in object detection as a ‘query by committee’ paradigm to choose the set of images to be queried and these methods outperform classical uncertainty-based active learning algorithms like maximum entropy. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Expand
Scalable Object Detection Using Deep Neural Networks
TLDR
This work proposes a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest. Expand
Feature Pyramid Networks for Object Detection
TLDR
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Scalable, High-Quality Object Detection
TLDR
It is demonstrated that learning-based proposal methods can effectively match the performance of hand-engineered methods while allowing for very efficient runtime-quality trade-offs. Expand
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
TLDR
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Expand
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TLDR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks. Expand
Rethinking the Inception Architecture for Computer Vision
TLDR
This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. Expand
Is Faster R-CNN Doing Well for Pedestrian Detection?
TLDR
A very simple but effective baseline for pedestrian detection, using an RPN followed by boosted forests on shared, high-resolution convolutional feature maps, presenting competitive accuracy and good speed. Expand
...
1
2
3
4
...