AI Paper Atlas

Research map / Architectures and efficiency / CNN design

UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale

Yuhao Wang, Wei Xi

ICCV 2025 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use progressive kernels (7,9,11) instead of (5,7,9) (ablation)UniConvNet-A · ImageNet-1K val, UniConvNet-A kernel ablationtop-1 accuracy: 76.6 -> 77.0Improved
use (7,9,11) instead of (9,11,13) (ablation)UniConvNet-A · ImageNet-1K val, UniConvNet-A kernel ablationtop-1 accuracy: 76.9 -> 77.0Improved
use (9,11,13) instead of (7,9,11) (ablation)UniConvNet-P0 · ImageNet-1K valtop-1 accuracy: 79.1 -> 79.3Mixed
use three progressive kernels (7,9,11) instead of (7,11,31) (ablation)UniConvNet-A · ImageNet-1K val, UniConvNet-A kernel ablationtop-1 accuracy: 76.0 -> 77.0Improved
use (7,9,11) instead of (7,9,29) (ablation)UniConvNet-A · ImageNet-1K val, UniConvNet-A kernel ablationtop-1 accuracy: 75.9 -> 77.0Improved
use (7,9,11) instead of (27,29,31) (ablation)UniConvNet-N2 · ImageNet-1K valtop-1 accuracy: 81.8 -> 82.7Improved
add Three-layer RFA large-kernel to DW3x3 model (ablation)UniConvNet-P0 · ImageNet-1K valtop-1 accuracy: 77.0 -> 78.9Improved
add modified DCNV3 to Three-layer RFA (ablation)UniConvNet-P0 · ImageNet-1K valtop-1 accuracy: 78.4 -> 79.1Improved
use modified DCNV3 instead of DW 3x3 (ablation)UniConvNet-P0 · ImageNet-1K valtop-1 accuracy: 78.9 -> 79.1Improved
use Three-layer RFA instead of DW 7x7 (ablation)UniConvNet-P0 · ImageNet-1K valtop-1 accuracy: 77.0 -> 79.1Improved
use Three-layer RFA instead of DW 7x7 (ablation)UniConvNet-N2 · ImageNet-1K valtop-1 accuracy: 81.0 -> 82.7Improved
add Three-layer RFA to 30M DW 3x3 model (ablation)UniConvNet-T · ImageNet-1K valtop-1 accuracy: 82.1 -> 84.2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

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