Methods › Computer Vision › Semantic Segmentation Modules › ASPP

Atrous Spatial Pyramid Pooling

ASPP

83 papers tagged archive 2025-07-28

Introduced by Liang-Chieh Chen et al. in DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

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

Atrous Spatial Pyramid Pooling (ASPP) is a semantic segmentation module for resampling a given feature layer at multiple rates prior to convolution. This amounts to probing the original image with multiple filters that have complementary effective fields of view, thus capturing objects as well as useful image context at multiple scales. Rather than actually resampling features, the mapping is implemented using multiple parallel atrous convolutional layers with different sampling rates.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 46 in the graph, strongest link: mentioned on GitHub). The lookup matched a different name in Syntology's graph, 'atrous spatial pyramid pooling (ASPP)' (resolution: alias); this answer is about that name. This answer is about arXiv:1606.00915, the paper the archive credits with this method.

Origin paper of this answer, arXiv:1606.00915 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 43 ran (of which 12 constructed an object rather than computing a result; 35 with no instrument failure: 1 honoured, 0 violated, 34 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified (of 63 harvested samples) · 18 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

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: 83 · with a code link: 45 · where Syntology ran a sample: 13 (13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (13 of 83 tagged: 13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 83 of 83, 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 117 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
Semantic Segmentation60
Segmentation41
Image Segmentation21
Object Detection13
Decoder11
object-detection10
Image Classification7
Instance Segmentation7
Medical Image Segmentation5
image-classification5
Autonomous Driving4
Data Augmentation4
Domain Adaptation4
Object4
Unsupervised Domain Adaptation4
Classification3
Medical Image Analysis3
Neural Architecture Search3
Transfer Learning3
Tumor Segmentation3

Usage over time archive 2025-07-28

Papers per year tagged with ASPP: 2016 to 2025, peak 16 16 0 2016: 1 paper 2016 2017: 1 paper 2017 2018: 5 papers 2018 2019: 10 papers 2019 2020: 10 papers 2020 2021: 16 papers 2021 2022: 13 papers 2022 2023: 9 papers 2023 2024: 11 papers 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (83 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

Semantic Segmentation Modules

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