AI Paper Atlas

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

When Unsupervised Domain Adaptation Meets Tensor Representations

Hao Lu, Lei Zhang, Zhiguo Cao, Wei Wei, Ke Xian, Chunhua Shen, Anton van den Hengel

ICCV 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 83 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 alignment matrices to naive tensor subspace learning (ablation)NTSL · Office-Caltech10 meanaccuracy (%): 85.3 -> 86.9Improved
add alignment matrices to naive tensor subspace learning (ablation)NTSL · ImageNet-VOC2007 mAPaverage precision (%): 58.4 -> 58.7No clear effect
add alignment matrices to naive tensor subspace learning (ablation)NTSL · Office-Caltech10 D->Caccuracy (%): 79.8 -> 84.0Improved
add alignment matrices to naive tensor subspace learning (ablation)NTSL · Office-Caltech10 W->Daccuracy (%): 97.8 -> 97.7No clear effect
adapt tensor representation directly instead of vectorized subspace alignment (SA)SA · Office-Caltech10 meanaccuracy (%): 74.3 -> 86.9Improved
adapt tensor representation directly instead of vectorized CORALCORAL · Office-Caltech10 meanaccuracy (%): 72.0 -> 86.9Improved
use TAISL instead of no adaptation on convolutional activationsNA · Office-Caltech10 meanaccuracy (%): 80.4 -> 86.9Improved
vector-form adaptation (PCA, TCA, DIP, SA, LTSL, CORAL) instead of no adaptationNA · Office-Caltech10 meanaccuracy (%): 80.4 -> 41.4Hurt
use TAISL instead of LSSA on W->CLSSA · Office-Caltech10 W->Caccuracy (%): 29.5 -> 82.6Improved
use TAISL instead of no adaptation on ImageNet-VOC2007NA · ImageNet-VOC2007 mAPaverage precision (%): 51.6 -> 58.7Improved
use TAISL instead of LSSA on A->CLSSA · Office-Caltech10 A->Caccuracy (%): 80.3 -> 80.1No clear effect
apply TAISL to HOG and VGG-M CONV5 tensor features (ablation)baseline features · Office-Caltech10 (two tasks)accuracyImproved

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