AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Convolutional Neural Networks Driven by Content Similarity

Ligeng Zou, Guihu Zhao

CVPR 2026 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention

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
add sorted 1D depth-wise convolution branch to gated convolution (ablation)Ego-T · ImageNet-1K valtop-1 accuracy (%): 83.5 -> 84.0Improved
enlarge 1D window from 6 ln(N)+1 to 24 ln(N)+1 (ablation)Ego-T · ImageNet-1K valtop-1 accuracy (%): 83.7 -> 84.0Improved
use global 1D convolution instead of window 24 ln(N)+1 (ablation)Ego-T · ImageNet-1K valtop-1 accuracy (%): 84.0 -> 84.0No clear effect
use linspace instead of logspace for weight decay (ablation)Ego-T · ImageNet-1K valtop-1 accuracy (%): 84.0 -> 83.9No clear effect
channel-wise sorting of tokens by feature similarity enlarges effective receptive field (ablation)Ego-T · effective receptive field visualizationinfluence region (qualitative)Improved
reduce COCO batch size from 16 to 8Ego-T · COCO val2017APbHurt
Ego-T vs MogaNet-S on detectionEgo-T · COCO val2017 (Cascade Mask R-CNN)APb: 51.6 -> 50.7Hurt
Ego-B vs MogaNet-B on detectionEgo-B · COCO val2017 (Cascade Mask R-CNN)APb: 52.6 -> 53.3Improved

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