Methods › Computer Vision › Convolutions › CoordConv

CoordConv

16 papers tagged archive 2025-07-28

Introduced by Rosanne Liu et al. in An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

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

A CoordConv layer is a simple extension to the standard convolutional layer. It has the same functional signature as a convolutional layer, but accomplishes the mapping by first concatenating extra channels to the incoming representation. These channels contain hard-coded coordinates, the most basic version of which is one channel for the i coordinate and one for the j coordinate.

The CoordConv layer keeps the properties of few parameters and efficient computation from convolutions, but allows the network to learn to keep or to discard translation invariance as is needed for the task being learned. This is useful for coordinate transform based tasks where regular convolutions can fail.

PaperSourceSee Code · uber-research/CoordConv

Papers archive 2025-07-28

16 shown of 16, 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 36 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 Detection5
object-detection4
Face Alignment3
Object3
Segmentation3
Decoder2
Deep Learning2
Real-Time Object Detection2
Semantic Segmentation2
2D Object Detection1
2D Semantic Segmentation1
Anatomical Landmark Detection1
Atari Games1
Breast Tissue Identification1
Decision Making1
Dense Object Detection1
Depth Estimation1
Depth Prediction1
Diagnostic1
Domain Adaptation1

Usage over time archive 2025-07-28

Papers per year tagged with CoordConv: 2018 to 2024, peak 4 4 0 2018: 2 papers 2018 2019: 1 paper 2019 2020: 4 papers 2020 2021: 4 papers 2021 2022: 2 papers 2022 2023: 1 paper 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (16 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

Convolutions

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