AI Paper Atlas

Research map / Detection and segmentation / CNN features

Co-Scale Conv-Attentional Image Transformers

Weijian Xu, Yifan Xu, Tyler Chang, Zhuowen Tu

ICCV 2021 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 464 citations (OpenAlex)

Read the paper

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 convolutional position encoding (CPE) and relative encoding (CRPE) together to CoaT-Lite Tiny with no position encoding (ablation)CoaT · ImageNet-1K val (CoaT-Lite Tiny)Top-1 accuracy (%): 68.8 -> 77.5Improved
add CRPE to CoaT-Lite Tiny without position encoding (ablation)CoaT · ImageNet-1K val (CoaT-Lite Tiny)Top-1 accuracy (%): 68.8 -> 75.0Improved
add CPE to CoaT-Lite Tiny without position encoding (ablation)CoaT · ImageNet-1K val (CoaT-Lite Tiny)Top-1 accuracy (%): 68.8 -> 75.9Improved
add CRPE on top of CPE (ablation)CoaT · ImageNet-1K val (CoaT-Lite Tiny)Top-1 accuracy (%): 75.9 -> 77.5Improved
add CPE on top of CRPE (ablation)CoaT · ImageNet-1K val (CoaT-Lite Tiny)Top-1 accuracy (%): 75.0 -> 77.5Improved
add co-scale with attention via feature interpolation to CoaT Tiny (ablation)CoaT · ImageNet-1K valTop-1 accuracy (%): 77.8 -> 78.3Improved
add co-scale with attention via feature interpolation to CoaT Tiny (detection) (ablation)CoaT · COCO Mask R-CNN FPN 1x box APAP: 41.6 -> 42.5Improved
add co-scale with direct cross-layer attention to CoaT Tiny (ablation)CoaT · ImageNet-1K valTop-1 accuracy (%): 77.8 -> 77.0Hurt
add co-scale with direct cross-layer attention to CoaT Tiny (detection) (ablation)CoaT · COCO Mask R-CNN FPN 1x box APAP: 41.6 -> 42.1Improved
use feature interpolation instead of direct cross-layer attention for co-scale (ablation)CoaT · ImageNet-1K valTop-1 accuracy (%): 77.0 -> 78.3Improved
use CoaT Small instead of ResNet-50 backbone in Deformable DETRCoaT · COCO Deformable DETR APAP: 44.5 -> 48.4Improved
add parallel group with co-scale (CoaT Small vs CoaT-Lite Small) on classification (ablation)CoaT · ImageNet-1K valTop-1 accuracy (%): 81.9 -> 82.1Improved

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