AI Paper Atlas

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

d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding

Xiang Xu, Xiong Zhou, Ragav Venkatesan, Gurumurthy Swaminathan, Orchid Majumder

CVPR 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 132 citations (OpenAlex)

Check 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
Use d-SNE instead of FADA with one labeled target example per classMNIST → USPS · MNIST → USPS, 1 target sample/classaccuracy: 89.10 -> 92.90Improved
Use d-SNE instead of CCSA with no labeled target examplesMNIST → USPS · MNIST → USPS, 0 target samples/classaccuracy: 65.40 -> 73.01Improved
Use d-SNE instead of CCSA with 10 labeled target examples per classMNIST → USPS · MNIST → USPSaccuracy: 97.27 ± 0.19 -> 99.00 ± 0.08Improved
Use d-SNE instead of the strongest listed unsupervised resultMNIST ↔ USPS · MNIST → USPSaccuracy: 98.26 ± 0.11 -> 99.00 ± 0.08Improved
Use supervised d-SNE instead of DIRT-TSVHN → MNIST · SVHN → MNISTaccuracy: 99.40 -> 96.45 ± 0.20Hurt
Add the semi-supervised extension to supervised d-SNEMNIST → MNIST-M · MNIST → MNIST-Maccuracy: 87.80 ± 0.16 -> 94.12Improved
Add the semi-supervised extension to supervised d-SNEMNIST → SVHN · MNIST → SVHNaccuracy: 61.73 ± 0.47 -> 77.63 ± 0.26Improved
Adapt the model to a target domain, then evaluate on the source domaind-SNE · MNIST → MNIST-M, source accuracyaccuracy: 99.45% -> 99.51%Improved
Adapt the model to a target domain, then evaluate on the source domaind-SNE · MNIST → SVHN, source accuracyaccuracy: 99.51% -> 99.59%Improved
Adapt the model to a target domain, then evaluate on the source domaind-SNE · SVHN → MNIST, source accuracyaccuracy: 88.96% -> 94.94%Improved
Use d-SNE with ResNet-101 instead of CCSA with VGG-16Office-31 · Office-31 average across six transfers, 3 target samples/classaccuracy: 85.80 -> 90.01Improved
Use d-SNE instead of CCSAVisDA-C · VisDA-C, synthetic → real, supervisedaccuracy: 76.89 -> 80.66Improved

Later papers that compared with this method

2 later accepted papers report d-SNE as a baseline in their results tables; 2 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