Methods › Computer Vision › Image Model Blocks › Inception Module

Inception Module

206 papers tagged archive 2025-07-28

Introduced by Christian Szegedy et al. in Going Deeper with Convolutions

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

An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter size, instead of being restricted to a single filter size, in a single image block, which we then concatenate and pass onto the next layer.

PaperSourceSee Code · hskang9/Googlenet

Papers archive 2025-07-28

30 shown of 206, 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 205 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
Image Classification35
General Classification30
image-classification29
Classification24
Deep Learning21
Object Detection21
Transfer Learning21
object-detection20
Quantization13
Object12
GPU11
Data Augmentation8
Object Recognition8
Autonomous Driving7
Clustering6
Prediction6
Diagnostic5
Domain Adaptation5
Medical Image Analysis5
Anomaly Detection4

Usage over time archive 2025-07-28

Papers per year tagged with Inception Module: 2014 to 2025, peak 35 35 0 2014: 3 papers 2014 2015: 14 papers 2015 2016: 18 papers 2016 2017: 24 papers 2017 2018: 16 papers 2018 2019: 22 papers 2019 2020: 35 papers 2020 2021: 20 papers 2021 2022: 10 papers 2022 2023: 19 papers 2023 2024: 19 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (206 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

Image Model Blocks

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