AI Paper Atlas

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

Deep Domain-Adversarial Image Generation for Domain Generalisation

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 423 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
augment source training examples with adversarially generated unseen-domain imagesDDAIG · Digits-DG Avg.accuracy: 73.7 -> 77.6Improved
learn a CNN transformation network rather than use gradient-based perturbationsDDAIG vs CrossGrad · PACS Avg.accuracy: 80.7 -> 83.1Improved
augment source data with generated unseen-domain imagesDDAIG · Office-Home Avg.accuracy: 64.7 -> 65.5Improved
augment source training data with generated imagesDDAIG · Market1501→DukeR1: 48.5 -> 50.6Improved
augment source training data with generated imagesDDAIG · Duke→Market1501R1: 57.7 -> 60.9Improved
vary transformation strength λ from 0.1 to 0.7 (ablation)DDAIG · Digits-DGaccuracy: 76.8; 76.8; 76.6; 76.8No clear effect
train with generated novel data only, removing source examples (ablation)DDAIG · Digits-DG Avg.accuracy: 73.7 -> 72.9Hurt
combine generated novel data with source data instead of using source data alone (ablation)DDAIG · Digits-DG Avg.accuracy: 73.7 -> 77.6Improved
add an STN before the perturbation network (ablation)DDAIG · Rotated MNIST 40°accuracy: 54.1 -> 61.1Improved
add an STN before the perturbation network (ablation)DDAIG · Rotated MNIST 50°accuracy: 40.3 -> 46.6Improved
use learned CNN perturbations instead of CrossGrad perturbationsDDAIG · Rotated MNIST 40°accuracy: 45.6 -> 54.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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