AI Paper Atlas

Research map / Architectures and efficiency

CNN design: research map

1,051 papers on CNN design in Architectures and efficiency, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 3 clusters and 13 approaches. The busiest year so far is 2018.

What it is

Design and theory of convolutional neural networks: efficient scalable CNNs, large and dynamic kernels, and networks that build in symmetries such as rotation (equivariant CNNs), along with analysis of what trained filters learn.

Terms you will see on this page:

Convolution
sliding a small learned filter over an image.
Equivariance
the output transforming predictably when the input is rotated or shifted.
Receptive field
the region of the input that affects one output.

Start reading with the most cited papers here:

Within Architectures and efficiency, its share shrank from 7.0% in 2023–24 to 2.9% in 2025–26 (137 → 102 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).

2016: 66162017: 93172018: 137182019: 133192020: 129202021: 115212022: 108222023: 77232024: 73242025: 64252026: 5626

Explore CNN design in the interactive map

Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.

What changed recently

Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):

Papers from 2025–2026 that are already cited most:

Approaches and key papers

CNN filters and inductive bias · 507 papers
Keywords: cnn, filter, trained

Approaches in this cluster:

Most cited and most cited since 2024:

Convolution and kernel design · 415 papers
Keywords: convolution, kernel, spatial

Approaches in this cluster:

Most cited and most cited since 2024:

Equivariant networks · 129 papers
Keywords: equivariant, equivariance, group

Approaches in this cluster:

Most cited and most cited since 2024:

Related topics in Architectures and efficiency

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy