AI Paper Atlas

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

DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks

Samyak Jain, Sravanti Addepalli, Pawan Kumar Sahu, Priyam Dey, R. Venkatesh Babu

CVPR 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 15 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
replace Mixed Training with DART's diversify-aggregate-repeat trainingWideResNet-28-10 · CIFAR-10accuracy: 97.69 std 0.19 -> 97.96 std 0.06Improved
replace Mixed Training with DART's diversify-aggregate-repeat trainingWideResNet-28-10 · CIFAR-100accuracy: 85.57 std 0.13 -> 86.46 std 0.12Improved
apply DART to SWADResNet-50 with SWAD · VLCS, PACS, OfficeHome, TerraIncognita, DomainNetOOD accuracy: 79.1 ± 0.1 -> 80.3 ± 0.2; 88.1 ± 0.1 -> 88.9 ± 0.1; 70.6 ± 0.2 -> 71.9 ± 0.1; 50.0 ± 0.3 -> 51.3 ± 0.2; 46.5 ± 0.1 -> 47Improved
add DART to MIROMIRO with CLIP ViT-B/16 · OfficeHomeOOD accuracy: 83.3 -> 87.37Improved
use diverse mixed augmentations across branches rather than the same augmentation in every branch (ablation)DART · CIFAR-100accuracy: DART Mixed-Train. 86.13; DART Cutout 84.15Improved
use DART with the same augmentation in every branch (ablation)DART · CIFAR-100accuracy: ERM + EMA 81.67 -> DART 82.31Improved
perform interpolation from the beginning rather than after common training (ablation)DART · CIFAR-100accuracy: 0.22%Hurt
increase interpolation interval beyond the useful range (ablation)DART · CIFAR-100accuracyHurt
increase the number of branches (ablation)DART · CIFAR-100accuracyImproved
delay a single interpolation for progressively longer after common training (ablation)DART · CIFAR-100accuracy: epoch-500 accuracy reaches 0Hurt
extend training beyond 300 epochs with DART rather than Mixed Training (ablation)DART vs ERM+EMA Mixed Training · CIFAR-100accuracyMixed

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