AI Paper Atlas

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

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

Lalit Pandey, Samantha Marie Waters Wood, Justin Newell Wood

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 7 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
train ViT-CoT on more images (0, 1.25k, 10k, 80k) (ablation)ViT-CoT · view-invariant object recognitionaccuracyImproved
increase ViT size from 3 to 6 or 9 heads/layers (ablation)ViT-CoT · view-invariant object recognitionaccuracyNo clear effect
reduce ViT to a single attention head/layer (ablation)ViT-CoT · view-invariant object recognitionaccuracyHurt
larger ViT-CoT versus smaller ViT-CoT data requirements (ablation)ViT-CoT · training-set size sweepaccuracyNo clear effect
train linear classifier on only one viewpoint range (N_train = 1) (ablation)ViT-CoT · view-invariant object recognitionaccuracyNo clear effect
replace ViT-CoT with VideoMAEViT · view-invariant object recognitionaccuracyNo clear effect
replace ViT-CoT with a CNN trained by SimCLR-CLTTViT-CoT · view-invariant object recognitionaccuracy: 7.3\%Improved
replace VideoMAE with a CNN trained by SimCLR-CLTTVideoMAE · view-invariant object recognitionaccuracy: 19.6\%Improved
use 2-frame instead of 3-frame learning window (ablation)ViT-CoT · view-invariant object recognitionaccuracyNo clear effect
raise image resolution from 64x64 to 224x224 (ablation)ViT-CoT and VideoMAE · view-invariant object recognitionaccuracyNo clear effect
replace supervised linear classifier with unsupervised decoder (2AFC) (ablation)ViT-CoT · 2AFC recognitionaccuracy: 62.1\% vs 50\% chanceImproved

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