Methods › Computer Vision › One-Stage Object Detection Models › SSD

SSD

278 papers tagged archive 2025-07-28

Introduced by Wei Liu et al. in SSD: Single Shot MultiBox Detector

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SSD is a single-stage object detection method that 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.

The fundamental improvement in speed comes from eliminating bounding box proposals and the subsequent pixel or feature resampling stage. Improvements over competing single-stage methods include using a small convolutional filter to predict object categories and offsets in bounding box locations, using separate predictors (filters) for different aspect ratio detections, and applying these filters to multiple feature maps from the later stages of a network in order to perform detection at multiple scales.

PaperSourceSee Code · amdegroot/ssd.pytorch

In Syntology about another paper, arXiv:2203.10759: repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The lookup matched a paper by its title, arXiv:2203.10759, not a method entry. About another paper: this answer is about arXiv:2203.10759, while the archive credits arXiv:1512.02325.

From the lookup's note on this name: The same name also belongs to the paper “SSD: Single Shot MultiBox Detector” (arXiv:1512.02325, 35,936 citations), which the lookup finds cited far more than the paper this answer is about (18 citations), so this answer may be about a different sense of the name. For arXiv:1512.02325: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2203.10759 (its page on this site · its page on Syntology).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 278 · with a code link: 110 · where Syntology ran a sample: 23 (17 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (23 of 278 tagged: 17 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 278, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 234 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Object Detection126
object-detection120
Object66
GPU16
Real-Time Object Detection16
Image Classification11
Deep Learning10
Pedestrian Detection10
Transfer Learning10
General Classification8
image-classification8
Autonomous Driving7
CPU7
Semantic Segmentation7
Classification6
regression6
2D Object Detection5
Benchmarking5
Clustering5
Quantization5

Usage over time archive 2025-07-28

Papers per year tagged with SSD: 2015 to 2025, peak 45 45 0 2015: 1 paper 2015 2016: 6 papers 2016 2017: 21 papers 2017 2018: 42 papers 2018 2019: 33 papers 2019 2020: 36 papers 2020 2021: 45 papers 2021 2022: 22 papers 2022 2023: 24 papers 2023 2024: 35 papers 2024 2025: 13 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (278 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

One-Stage Object Detection ModelsObject Detection Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections