SSD: Single Shot MultiBox Detector. 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 300×300 input, SSD achieves 72.1% mAP on VOC2007 test at 58 FPS on a Nvidia Titan X and for 500×500 input, SSD achieves 75.1% mAP, outperforming a comparable state of the art Faster R-CNN model.

References in zbMATH (referenced in 14 articles )

Showing results 1 to 14 of 14.
Sorted by year (citations)

  1. Jia, Fan; Liu, Jun; Tai, Xue-Cheng: A regularized convolutional neural network for semantic image segmentation (2021)
  2. Amosov, O. S.; Amosova, S. G.; Zhiganov, S. V.; Ivanov, Yu. S.; Pashchenko, F. F.: Computational method for recognizing situations and objects in the frames of a continuous video stream using deep neural networks for access control systems (2020)
  3. Chen, Liqiong; Zou, Lian; Fan, Cien; Liu, Yifeng: Feature weighting network for aircraft engine defect detection (2020)
  4. Chen, Ruidian; He, Jingsong: Two-stage training method of retinanet for bird’s nest detection (2020)
  5. Chigrinskii, V. V.; Matveev, I. A.: Optimization of a tracking system based on a network of cameras (2020)
  6. Daniel Bolya, Sean Foley, James Hays, Judy Hoffman: TIDE: A General Toolbox for Identifying Object Detection Errors (2020) arXiv
  7. Teng, Hao; Lu, Huijuan; Ye, Minchao; Yan, Ke; Gao, Zhigang; Jin, Qun: Applying of adaptive threshold non-maximum suppression to pneumonia detection (2020)
  8. Wang, Sen; Xing, Yuxiang; Zhang, Li; Gao, Hewei; Zhang, Hao: Deep convolutional neural network for ulcer recognition in wireless capsule endoscopy: experimental feasibility and optimization (2019)
  9. Haifeng Jin, Qingquan Song, Xia Hu: Auto-Keras: An Efficient Neural Architecture Search System (2018) arXiv
  10. Liao, Minghui; Shi, Baoguang; Bai, Xiang: TextBoxes++: a single-shot oriented scene text detector (2018)
  11. Rishabh Iyer, Pratik Dubal, Kunal Dargan, Suraj Kothawade, Rohan Mahadev, Vishal Kaushal: Vis-DSS: An Open-Source toolkit for Visual Data Selection and Summarization (2018) arXiv
  12. Yu, Hancheng; Qin, Haibao; Peng, Maoting: A fast approach to texture-less object detection based on orientation compressing map and discriminative regional weight (2018)
  13. Zhu, Chao; Yin, Xu-Cheng: Effective human detection via multi-model classification and adaptive late fusion (2018)
  14. Zhang, Jianming; Huang, Manting; Jin, Xiaokang; Li, Xudong: A real-time Chinese traffic sign detection algorithm based on modified YOLOv2 (2017)