AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Peripheral Vision Transformer

Juhong Min, Yucheng Zhao, Chong Luo, Minsu Cho

NeurIPS 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 18 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-based peripheral attention Phi_p (ablation)PerViT-T · ImageNet-1K valTop-1 accuracy: 77.3 -> 78.8Improved
add position-based peripheral attention Phi_p (ablation)PerViT-S · ImageNet-1K valTop-1 accuracy: 81.1 -> 82.1Improved
add position-based peripheral attention Phi_p (ablation)PerViT-M · ImageNet-1K valTop-1 accuracy: 81.9 -> 82.9Improved
add content-based attention Phi_c (ablation)PerViT-T · ImageNet-1K valTop-1 accuracy: 76.8 -> 78.8Improved
add convolutional stem (ablation)PerViT-T · ImageNet-1K valTop-1 accuracy: 77.8 -> 78.8Improved
add convolutional position encoding (CPE) (ablation)PerViT-T · ImageNet-1K valTop-1 accuracy: 78.1 -> 78.8Improved
add C-Stem and CPE (ablation)PerViT without Phi_p · ImageNet-1K valTop-1 accuracy: T: 72.2 -> 77.3; S: 79.8 -> 81.1; M: 81.8 -> 81.9Improved
peripheral initialization instead of convolutional initialization (ablation)PerViT-T Phi_p · ImageNet-1K valTop-1 accuracy: 78.6 -> 78.8Improved
peripheral initialization instead of random initialization (ablation)PerViT-T Phi_p · ImageNet-1K valTop-1 accuracy: 78.5 -> 78.8Improved
add peripheral projection (neighbors) and multi-layer jointly (ablation)Phi_p with Euclidean distance · ImageNet-1K valTop-1 accuracy: 78.0 -> 78.8Improved
add multi-layer projection alone (no peripheral projection) (ablation)Phi_p with Euclidean distance · ImageNet-1K valTop-1 accuracy: 78.0 -> 77.9No clear effect
Euclidean distance embedding instead of learnable vectors (ablation)Phi_p · ImageNet-1K valTop-1 accuracy: 77.8 -> 78.8Improved

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