AI Paper Atlas

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

Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift

Ryuhei Takahashi, Atsushi Hashimoto, Motoharu Sonogashira, Masaaki Iiyama

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 13 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 partially shared weights and VAE to D-CycleGAN (ablation)D-CycleGAN · Human pose estimation, Avg. error < 10pxaccuracy %: 50.8 -> 57.0Improved
add feature disentanglement into domain-invariant and specific parts (ablation)CycleGAN+L_fc · Human pose estimation, Avg. error < 10pxaccuracy %: 35.5 -> 50.8Improved
add VAE (KL loss and resampling) without weight sharing (ablation)D-CycleGAN · Human pose estimation, Avg. error < 10pxaccuracy %: 50.8 -> 18.6Hurt
add partial weight sharing without VAE (ablation)D-CycleGAN · Human pose estimation, Avg. error < 10pxaccuracy %: 50.8 -> 42.1Hurt
add VAE on top of partially shared auto-encoders (ablation)PS-AEs · Human pose estimation, Avg. error < 10pxaccuracy %: 42.1 -> 57.0Improved
use PS-VAEs instead of CyCADACyCADA · Human pose estimation, Avg. error < 10pxaccuracy %: 41.0 -> 57.0Improved
use PS-VAEs instead of MCDMCD · Human pose estimation, Avg. error < 10pxaccuracy %: 5.3 -> 57.0Improved
use PS-VAEs instead of CyCADA at heaviest imbalanceCyCADA · MNIST->USPS 50% imbalanceaccuracy: 87.6 -> 92.6Improved
use PS-VAEs instead of UFDN at heaviest imbalanceUFDN · USPS->MNIST 50% imbalanceaccuracy: 69.1 -> 82.4Improved
increase class-1 imbalance from 10% to 50% for PS-VAEsPS-VAEs · MNIST->USPSaccuracy: 93.9 -> 92.6No clear effect
increase class-1 imbalance from 10% to 50% for UFDNUFDN · SVHN->MNISTaccuracy: 91.1 -> 43.6Hurt
use PS-VAEs instead of MCD on SVHN->MNIST at 10%MCD · SVHN->MNIST 10%accuracy: 90.3 -> 73.7Hurt

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