AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer

Haokui Zhang, Wenze Hu, Xiaoyu Wang

ECCV 2022 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 94 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
add position embedding to ParC (ablation)ParC-Net-S · MS-COCO detectionmAP: 27.5 -> 28.5Improved
add position embedding to ParC (ablation)ParC-Net-S · PASCAL VOC segmentationmIOU: 79.2 -> 79.7Improved
add position embedding to ParC (ablation)ParC-Net-S · ImageNet-1k classificationtop-1: 78.63 -> 78.63No clear effect
use meta-former architecture instead of ResNeXt block (ablation)ParC-Net-S · ImageNet-1k classificationtop-1: 76.00 -> 78.63Improved
add channel-wise attention (ablation)ParC-Net-S · ImageNet-1k classificationtop-1: 78.50 -> 78.63Improved
use ParC instead of big kernel 1/4 (ablation)ParC-Net-S · ImageNet-1k classificationtop-1: 78.46 -> 78.63Improved
increase big kernel size from 1/4 to 1/2 of input (ablation)big-kernel variant · ImageNet-1k classificationtop-1: 78.46 -> 78.45No clear effect
replace ViT blocks of MobileViT-S with ParC blocksMobileViT-S · ImageNet-1k classificationtop-1 / params: 78.4 -> 78.6; 5.6M -> 5.0M paramsImproved
replace ViT blocks with ParC blocks (RK3288 latency)MobileViT-S · RK3288 latencyms: 457 -> 353Improved
replace ViT blocks with ParC blocks (DP2000 latency)MobileViT-S · DP2000 latencyms: 368 -> 98Improved
insert ParC into ResNet50ResNet50 · ImageNet-1k classificationtop-1: 78.8 -> 79.6Improved
insert ParC into MobileNetV2MobileNetV2 · ImageNet-1k classificationtop-1: 70.2 -> 71.1; latency 24 -> 27 msMixed

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