AI Paper Atlas

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

DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation

Bharath Bhushan Damodaran, Benjamin Kellenberger, Remi Flamary, Devis Tuia, Nicolas Courty

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 469 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
compute optimal transport coupling in deep CNN feature layer instead of image space (ablation)JDOT/DeepJDOT · MNIST -> MNIST-Mtarget accuracy: 66.7 -> 92.4Improved
compute coupling in deep features instead of image space (ablation)JDOT/DeepJDOT · SVHN -> MNISTtarget accuracy: 67.6 -> 96.7Improved
compute coupling in deep features instead of image space (ablation)JDOT/DeepJDOT · USPS -> MNISTtarget accuracy: 90.5 -> 96.4Improved
add source classification loss Ls to the JDOT loss (ablation)DeepJDOT · USPS -> MNISTtarget accuracy: 86.41 -> 96.4Improved
add source classification loss Ls to the JDOT loss (ablation)DeepJDOT · MNIST -> MNIST-Mtarget accuracy: 73.6 -> 92.4Improved
add target pseudo-label transport loss Lt (ablation)DeepJDOT (Ls + alpha d) · MNIST -> MNIST-Mtarget accuracy: 82.3 -> 92.4Improved
add target pseudo-label transport loss Lt (ablation)DeepJDOT (Ls + alpha d) · USPS -> MNISTtarget accuracy: 95.53 -> 96.4Improved
apply DeepJDOT adaptationsource-only CNN · MNIST -> MNIST-Mtarget accuracy: 60.8 -> 92.4Improved
apply DeepJDOT adaptationsource-only CNN · MNIST -> USPStarget accuracy: 94.8 -> 95.7No clear effect
apply DeepJDOT adaptationsource-only ResNet-50 · VisDA-2017 meanaccuracy: 28.0 -> 66.9Improved
apply DeepJDOT adaptationsource-only ResNet-50 · VisDA-2017 car classaccuracy: 94.7 -> 87.3Hurt
use DeepJDOT instead of DAHVGG-16 · Office-Home meanaccuracy: 45.54 -> 50.67Improved

Later papers that compared with this method

4 later accepted papers report DeepJDOT as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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