AI Paper Atlas

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

Write a Classifier: Predicting Visual Classifiers from Unstructured Text

Mohamed Elhoseiny, Ahmed Elgammal, Babak Saleh

TPAMI 2016 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 35 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 seen-example negative-side constraints (ablation)linear formulation E · Oxford Flowers (one fold)avg AUC: 0.59 -> 0.65Improved
add constraint t*^T W c >= l (ablation)linear formulation E · Oxford Flowers (one fold)avg AUC: 0.58 -> 0.65Improved
combine regression (TGP) and domain transfer with constraintslinear classifier prediction · Oxford Flowersavg AUC: 0.62 -> 0.68Improved
combine regression (TGP) and domain transfer with constraintslinear classifier prediction · CUB Birdsavg AUC: 0.61 -> 0.62Improved
add constraints to GPRGPR · Oxford Flowersavg AUC: 0.54 -> 0.62Improved
add constraints to TGPTGP · Oxford Flowersavg AUC: 0.58 -> 0.63Improved
add constraints to domain transfer (CDT)DT · Oxford Flowersavg AUC: 0.62 -> 0.64Improved
use constrained DT alone (gamma=0, no TGP term) (ablation)formulation E · Oxford Flowersavg AUC: 0.64 -> 0.68Hurt
predict kernel classifier with one-class SVM adjusted DT instead of linear classifierDT-based prediction · Flower|Nsc| to |Nsc+1| recall (%): 31.33 -> 40.34Improved
predict kernel classifier with one-class SVM adjusted DT instead of linear classifierDT-based prediction · CUB Birds|Nsc| to |Nsc+1| recall (%): 36.56 -> 44.05Improved
replace linear classifier with SVM-DT kernelclassifier prediction · FlowerMAU (%): 5.93 -> 9.1Improved
replace linear classifier with SVM-DT kernelclassifier prediction · CUB Birds (MKL image kernel)MAU (%): 2.74 -> 4.10Improved

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