mlsanityData to 14 Oct 2026

SSD: Single Shot MultiBox Detector

arXiv 1512.02325 ↗First posted 8 Dec 2015cs.CVcited by 3,130

Not on the map. Why?

Cited by 53 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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. Code is available at https://github.com/weiliu89/caffe/tree/ssd .

Key facts. Cited by 3,130 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 3; 2021: 865; 2022: 708; 2023: 596; 2024: 447; 2025: 336; 2026: 173.

3,130 papers.

Sort:

By area:

  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  2. 2021Transformers in Vision: A Surveycited by 1,013
  3. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  4. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  5. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  6. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  7. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 503
  8. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  9. 2021Conditional DETR for Fast Training Convergencecited by 424
  10. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  11. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 349
  12. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
38 more
  1. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 311
  2. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 308
  3. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  4. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 305
  5. 2021Towards Open World Object Detectioncited by 297
  6. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  7. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  8. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  9. 2021Oriented R-CNN for Object Detectioncited by 231
  10. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  11. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 204
  12. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
  13. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
  14. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
  15. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  16. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  17. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  18. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  19. 2022DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detectioncited by 176
  20. 2021ASFormer: Transformer for Action Segmentationcited by 168
  21. 2021Multimodal Virtual Point 3D Detectioncited by 166
  22. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  23. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  24. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 160
  25. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 159
  26. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  27. 2021Instances as Queriescited by 158
  28. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
  29. 2022DETRs with Hybrid Matchingcited by 150
  30. 2022Multiview Transformers for Video Recognitioncited by 148
  31. 2021Focal and Global Knowledge Distillation for Detectorscited by 142
  32. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  33. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  34. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  35. 2021Probabilistic two-stage detectioncited by 130
  36. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  37. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  38. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128

50 most cited of 3,130 All 3,130 (JSON)