AI Paper Atlas

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

Background Invariance Testing According to Semantic Proximity

Zukang Liao, Min Chen

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 0 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
use ontology-expanded keywords instead of random samplingbackground sampling · Background invariance testing (250 IN9 models, N=32)F1 score: 0.491 -> 0.650Improved
use ontology keywords instead of CLIP keywordskeyword-based sampling · Background invariance testing (250 IN9 models, N=32)F1 score: 0.615 -> 0.650Improved
use ontology keywords instead of interval samplingbackground sampling · Background invariance testing (250 IN9 models, N=32)F1 score: 0.591 -> 0.650Improved
use ontology instead of nearest top-K samplingbackground sampling · Background invariance testing (250 IN9 models, N=32)neuron coverage (recall): 0.133 -> 0.652Improved
use ontology instead of nearest top-K samplingbackground sampling · Background invariance testing (250 IN9 models, N=32)Fleiss reliability (precision): 0.906 -> 0.649Hurt
use ontology instead of random samplingbackground sampling · Background invariance testing (250 IN9 models, N=32)Fleiss reliability (precision): 0.384 -> 0.649Improved
use ontology instead of random samplingbackground sampling · Background invariance testing (250 IN9 models, N=32)neuron coverage (recall): 0.681 -> 0.652Hurt
increase number of selected test images from 32 to 100 (ablation)ontology sampling · Background invariance testing (250 IN9 models, N=32)F1 score: 0.650 -> 0.652No clear effect
increase number of selected test images from 32 to 50 (ablation)ontology sampling · Background invariance testing (250 IN9 models, N=32)F1 score: 0.650 -> 0.651No clear effect
use Random Forest instead of AdaBoost as assessorautomated assessor · Automated assessor on IN9 model repository (RBF size 32, sigma 10)automation accuracy (%): 74.8 -> 79.7Improved
change RBF interpolation settings from size 32 sigma 10 to size 16 sigma 5 (ablation)Random Forest assessor · Automated assessor on IN9 model repository (RBF size 32, sigma 10)automation accuracy (%): 79.7 -> 78.7No clear effect
use larger sigma in RBF interpolation (sigma 10 vs 2) (ablation)AdaBoost assessor · Automated assessor on IN9 model repository (RBF size 32, sigma 10)automation accuracy (%): 54.5 -> 74.8Improved

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