AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

"Contributions of Shape, Texture, and Color in Visual Recognition"

Yunhao Ge, Yao Xiao, Zhi Xu, Xingrui Wang, Laurent Itti

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 42 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
combine shape, texture and color nets instead of shape net alone (ablation)Humanoid NN · Shape-biased subsetaccuracy: 90% -> 95%Improved
combine three feature nets instead of texture net alone (ablation)Humanoid NN · Texture-biased subsetaccuracy: 81% -> 91%Improved
combine three feature nets instead of color net alone (ablation)Humanoid NN · Color-biased subsetaccuracy: 82% -> 92%Improved
decompose image into three feature nets instead of original ResNet-18 (ablation)Humanoid NN · Color-biased subsetaccuracy: 95% -> 92%Hurt
add color to shape+texture inputs (ablation)Humanoid NN · Color-biased subsetaccuracy: 83% -> 92%Improved
add shape to texture+color inputs (ablation)Humanoid NN · Shape-biased subsetaccuracy: 86% -> 95%Improved
add shape to texture+color inputs (ablation)Humanoid NN · Texture-biased subsetaccuracy: 83% -> 90%Improved
replace MLP aggregation with average pooling (ablation)Humanoid NN · Color-biased subsetcolor contribution ratio: 70% -> 95%Mixed
replace MLP aggregation with average pooling (ablation)Humanoid NN · Texture-biased subsettexture contribution ratio: 65% -> 79%Mixed
vary random seed of texture extractor (ablation)Humanoid NN · Texture-biased subsettexture contribution ratio: 62.4% ± 2.3%No clear effect
use HVE cross-feature GAN instead of three pix2pix GANsimagination · color inputFID: 203.527 -> 52.846Improved
use HVE cross-feature GAN instead of three pix2pix GANsimagination · shape inputFID: 123.915 -> 96.871Improved

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