SSD: Single Shot MultiBox Detector
By Wei David Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott E. Reed, Cheng-Yang Fu, Alexander C. Berg. 2015
35,476 citations recorded by the source corpus.
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 feature maps with different resolutions to naturally handle objects of various sizes. Our SSD model is simple relative to methods that require object proposals because it completely eliminates proposal generation and subsequent pixel or feature resampling stage and encapsulates all computation in a single network. This makes SSD easy to train and straightforward to integrate into systems that require a detection component. Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference. Compared to other single stage methods, SSD has much better accuracy, even with a smaller input image size. For $300\times 300$ input, SSD achieves 72.1% mAP on VOC2007 test at 58 FPS on a Nvidia Titan X and for $500\times 500$ input, SSD achieves 75.1% mAP, outperforming a comparable state of the art Faster R-CNN model. Code is available at this https URL .
Subfields: Computer Vision and Pattern Recognition
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
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Trevor Darrell
- Jitendra Malik
- Yi Yang
- Andrew Zisserman
Citations in the corpus
- End-to-End Object Detection with Transformers (2020, methodology): “Several object detectors [9,25,35] used the bipartite matching loss.”
- Rethinking ImageNet Pre-Training (2018, background): “As modern object detectors [9, 15, 8, 36, 35, 28, 26, 13] evolved under the pre-training paradigm, the belief that training from scratch is non-trivial became conventional wisdom.”
- Mixed Precision Training (2017, methodology): “As an example, consider Figure 3 showing the histogram of activation gradient values, collected across all layers during FP32 training of Multibox SSD detector network (Liu et al., 2015a).”
- Exploring Self-Attention for Image Recognition (2020, background): “These serve as the basis for models developed for other computer vision tasks, such as semantic segmentation [22, 3, 42, 44] and object detection [10, 9, 28, 21].”
- Relation Networks for Object Detection (2017, neutral): “3Another object detection paradigm is based on dense sliding windows [35, 37, 33].”
- Randaugment: Practical automated data augmentation with a reduced search space (2019, background): “Object-centric cropping is commonly used for object detection tasks [24], whereas [8] adds new objects on training images by cut-and-paste.”
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features (2019, methodology): “However, the pre-training with CutMix improves the performance of both SSD and Faster-RCNN.”
- Feature Pyramid Networks for Object Detection (2016, methodology): “The Single Shot Detector (SSD) [22] is one of the first attempts at using a ConvNet’s pyramidal feature hierarchy as if it were a featurized image pyramid (Fig.”
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, background): “In recent years, with the development of convolutional neural network (CNN), object detection has been dominated by anchor-based detectors, which can be generally divided into one-stage methods [36, 33]”
- Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “SSD [39] detects objects in a way similar to the RPN [46], but uses multiple”
- Objects as Points (2019, background): “Our approach is closely related to anchor-based one-stage approaches [33, 36, 43].”
- FCOS: Fully Convolutional One-Stage Object Detection (2019, methodology): “The design of anchor boxes are pop-ularized by Faster R-CNN in its RPNs [20], SSD [15] and YOLOv2 [18], and has become the convention in a modern detector.”
- Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression (2019, background): “Most popular object detectors [20, 21, 3, 12, 13, 16] utilize some combination of the bounding box representations and losses mentioned above.”
- Panoptic Feature Pyramid Networks (2019, methodology): “Our competition entry was trained with color augmentation [40] and at test time balanced the class distribution and used multi-scale inference.”
- Learning Non-maximum Suppression (2017, background): “This last stage is commonly referred to as “non-maximum suppression” (NMS) [10, 9, 21, 7, 20, 16].”
- Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “Subsequently, it has been applied to multiple tasks like feature point detection [18, 11, 19], face detection [27] and object detection [3, 7, 9].”
- DeepSetNet: Predicting Sets with Deep Neural Networks (2016, methodology): “Deep neural networks have shown state-of-the-art performance on many computer vision problems, including semantic segmentation [33], visual tracking [31], image captioning [21], scene classification [22], and object detection [27].”
- Fully Convolutional Instance-Aware Semantic Segmentation (2016, background): “For the finer scales, a random 600×600 image patch is cropped for training due to memory issues, as in [27].”
- Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors (2016, methodology): “In our paper we focus primarily on three recent (meta)architectures: SSD (Single Shot Multibox Detector [25]), Faster R-CNN [30] and R-FCN (Region-based Fully Convolutional Networks [6]).”
- Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, methodology): “If we use the state-of-the-art object detector, Single Shot MultiBox Detector (SSD)[22], the performance drops 10% .”