AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Fine-Grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach

Timnit Gebru, Judy Hoffman, Li Fei-Fei

ICCV 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 155 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 attribute classifiers and attribute consistency loss (ablation)Source CNN · Cars->GSV unsupervised adaptation (all GSV val classes)accuracy (%): 9.28 -> 14.37Improved
add attribute classifiers without consistency loss (ablation)Source CNN · Cars->GSV unsupervised adaptation (all GSV val classes)accuracy (%): 9.28 -> 10.80Improved
add consistency loss on top of attribute classifiers (ablation)Source CNN w/att · Cars->GSV unsupervised adaptation (all GSV val classes)accuracy (%): 10.80 -> 14.37Improved
add attribute losses and consistency loss to domain confusion (ablation)DC · Cars->GSV unsupervised adaptation (all GSV val classes)accuracy (%): 14.98 -> 19.05Improved
add attribute losses and consistency loss to semi-supervised DC (ablation)DC · Cars->GSV semi-supervised adaptation (held-out GSV classes)accuracy (%): 12.34 -> 19.11Improved
add attributes and consistency loss to S+T CNN (ablation)S+T CNN · Cars->GSV semi-supervised adaptation (held-out GSV classes)accuracy (%): 4.12 -> 7.45Improved
add WordNet-label classifiers without consistency loss (ablation)Source CNN · Office Amazon->Webcam unsupervisedaccuracy (%): 60.9 -> 59.5Hurt
add WordNet-label classifiers and consistency loss (ablation)Source CNN · Office Amazon->Webcam unsupervisedaccuracy (%): 60.9 -> 61.2No clear effect
add WordNet-label losses and consistency loss to DC (ablation)DC · Office Amazon->Webcam unsupervisedaccuracy (%): 61.1 -> 62.4Improved
add WordNet-label losses and consistency loss to semi-supervised DC (ablation)DC · Office Amazon->Webcam semi-supervisedaccuracy (%): 47.0 -> 51.8Improved
add WordNet-label classifiers and consistency loss to S+T CNN (ablation)S+T CNN · Office Amazon->Webcam semi-supervisedaccuracy (%): 45.5 -> 45.3No clear effect
add domain confusion without attributesSource CNN · Cars->GSV unsupervised adaptation (all GSV val classes)accuracy (%): 9.28 -> 14.98Improved

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