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

Papers archive 2025-07-28

30 shown of 83, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

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