SOTAVerified

Domain Generalization

The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain

Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning

Papers

Showing 476500 of 1751 papers

TitleStatusHype
Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen DomainsCode1
In Search of Lost Domain GeneralizationCode1
Measuring Robustness to Natural Distribution Shifts in Image ClassificationCode1
Improving robustness against common corruptions by covariate shift adaptationCode1
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution GeneralizationCode1
PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo MatchingCode1
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent AlignmentCode1
Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-IdentificationCode1
A Universal Representation Transformer Layer for Few-Shot Image ClassificationCode1
Frustratingly Simple Domain Generalization via Image StylizationCode1
Domain Generalization using Causal MatchingCode1
Style Normalization and Restitution for Generalizable Person Re-identificationCode1
Selecting Data Augmentation for Simulating InterventionsCode1
Single-Side Domain Generalization for Face Anti-SpoofingCode1
Towards Data-Efficient Learning: A Benchmark for COVID-19 CT Lung and Infection SegmentationCode1
Regularizing Meta-Learning via Gradient DropoutCode1
Test-Time Adaptable Neural Networks for Robust Medical Image SegmentationCode1
Efficient Domain Generalization via Common-Specific Low-Rank DecompositionCode1
Generalizable Model-agnostic Semantic Segmentation via Target-specific NormalizationCode1
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the WildCode1
Out-of-Distribution Generalization via Risk Extrapolation (REx)Code1
On Feature Normalization and Data AugmentationCode1
Cross-Domain Few-Shot Classification via Learned Feature-Wise TransformationCode1
AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyCode1
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case GeneralizationCode1
Show:102550
← PrevPage 20 of 71Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SIMPLE+Average Accuracy99Unverified
2PromptStyler (CLIP, ViT-L/14)Average Accuracy98.6Unverified
3GMDG (RegNetY-16GF, SWAD)Average Accuracy97.9Unverified
4D-Triplet(RegNetY-16GF)Average Accuracy97.6Unverified
5MoA (OpenCLIP, ViT-B/16)Average Accuracy97.4Unverified
6GMDG (e RegNetY-16GF)Average Accuracy97.3Unverified
7PromptStyler (CLIP, ViT-B/16)Average Accuracy97.2Unverified
8SPG (CLIP, ViT-B/16)Average Accuracy97Unverified
9CAR-FT (CLIP, ViT-B/16)Average Accuracy96.8Unverified
10MIRO (RegNetY-16GF, SWAD)Average Accuracy96.8Unverified
#ModelMetricClaimedVerifiedStatus
1ViT-8/B-224Accuracy - Clean Images450Unverified
2VOLO-D5Accuracy - All Images57.2Unverified
3ConvNeXt-BAccuracy - All Images53.5Unverified
4ResNeXt-101 32x16dAccuracy - All Images51.7Unverified
5EfficientNet-B8 (advprop+autoaug)Accuracy - All Images50.5Unverified
6EfficientNet-B7 (advprop+autoaug)Accuracy - All Images49.7Unverified
7EfficientNet-B6 (advprop+autoaug)Accuracy - All Images49.6Unverified
8EfficientNet-B5 (advprop+autoaug)Accuracy - All Images49.1Unverified
9ViT-16/L-224Accuracy - All Images49Unverified
10ResNet-50 (gn)Accuracy - All Images48.9Unverified