AI Paper Atlas

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

Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation

Jinghua Wang, Jianmin Jiang

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 50 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 RT/IRT task classifiers for representation alignment (ablation)CoCoGAN w/o T · Zero-shot DA on MNIST/Fashion-MNIST/NIST/EMNIST, averageaccuracy (%): +15.6% on averageImproved
add task classifiers (NIST RT, IRT Fashion-MNIST, color->gray) (ablation)CoCoGAN w/o T · NIST, color->grayaccuracy (%): 30.9 -> 57.7Improved
add task classifiers (MNIST RT, IRT EMNIST, color->gray) (ablation)CoCoGAN w/o T · MNIST, color->grayaccuracy (%): 63.5 -> 94.7Improved
add task classifiers (MNIST RT, IRT Fashion-MNIST, gray->color) (ablation)CoCoGAN w/o T · MNIST, gray->coloraccuracy (%): 68.3 -> 78.1Improved
add task classifiers (Fashion-MNIST RT, IRT NIST, gray->color) (ablation)CoCoGAN w/o T · Fashion-MNIST, gray->coloraccuracy (%): 39.7 -> 56.8Mixed
add task classifiers (NIST RT, IRT MNIST, gray->negative) (ablation)CoCoGAN w/o T · NIST, gray->negativeaccuracy (%): 39.3 -> 45.7Improved
add task classifiers to improve generated-image correspondence (ablation)CoCoGAN w/o T · MNIST, gray->edgeoverlap ratio: 0.816 -> 0.873Improved
add task classifiers to improve generated-image correspondence (ablation)CoCoGAN w/o T · MNIST, gray->negativeoverlap ratio: 0.804 -> 0.863Improved
use CoCoGAN instead of ZDDA, NIST with digit IRT (color->gray)ZDDA · NIST, color->gray, IRT MNISTaccuracy (%): +7.9%Improved
use CoCoGAN instead of ZDDA, NIST with fashion IRT (color->gray)ZDDA · NIST, color->gray, IRT Fashion-MNISTaccuracy (%): 23.7 -> 57.7Improved
use CoCoGAN instead of ZDDA, MNIST with EMNIST IRT (gray->color)ZDDA · MNIST, gray->coloraccuracy (%): 94.8 -> 95.6Improved
use CoCoGAN with no target data versus methods that use target data (color->gray MNIST)existing DA methods with target data · MNIST, color->grayaccuracy (%): 94.2 -> 94.7Improved

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