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 101150 of 1751 papers

TitleStatusHype
Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution GeneralizationCode1
Domain Decorrelation with Potential Energy RankingCode1
Which Invariance Should We Transfer? A Causal Minimax Learning ApproachCode1
Adaptive High-Frequency Transformer for Diverse Wildlife Re-IdentificationCode1
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image SegmentationCode1
Aggregated Residual Transformations for Deep Neural NetworksCode1
A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip DesignCode1
Collaborating Foundation Models for Domain Generalized Semantic SegmentationCode1
Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization PerspectiveCode1
Compound Text-Guided Prompt Tuning via Image-Adaptive CuesCode1
Causality Inspired Representation Learning for Domain GeneralizationCode1
ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain GeneralizationCode1
Adaptive Risk Minimization: Learning to Adapt to Domain ShiftCode1
Causality-inspired Single-source Domain Generalization for Medical Image SegmentationCode1
Distribution Shift Inversion for Out-of-Distribution PredictionCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Contrastive Syn-to-Real GeneralizationCode1
Domain-General Crowd Counting in Unseen ScenariosCode1
A Closer Look at Few-shot ClassificationCode1
Anatomy of Domain Shift Impact on U-Net Layers in MRI SegmentationCode1
An Empirical Framework for Domain Generalization in Clinical SettingsCode1
Crafting Distribution Shifts for Validation and Training in Single Source Domain GeneralizationCode1
UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation PipelineCode1
Cross-Domain Ensemble Distillation for Domain GeneralizationCode1
MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-LabelingCode1
An Information-theoretic Approach to Distribution ShiftsCode1
A Fourier-based Framework for Domain GeneralizationCode1
AFN: Adaptive Fusion Normalization via an Encoder-Decoder FrameworkCode1
CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from SimulationCode1
Making Convolutional Networks Shift-Invariant AgainCode1
AdvST: Revisiting Data Augmentations for Single Domain GeneralizationCode1
Causal Balancing for Domain GeneralizationCode1
Cross-Domain Few-Shot Classification via Learned Feature-Wise TransformationCode1
DIVA: Domain Invariant Variational AutoencodersCode1
DomainDrop: Suppressing Domain-Sensitive Channels for Domain GeneralizationCode1
Domain generalization of 3D semantic segmentation in autonomous drivingCode1
Adversarial Training for Free!Code1
Disentangling Masked Autoencoders for Unsupervised Domain GeneralizationCode1
Calibrated Feature Decomposition for Generalizable Person Re-IdentificationCode1
Disentangled Feature Representation for Few-shot Image ClassificationCode1
Leveraging Vision-Language Models for Improving Domain Generalization in Image ClassificationCode1
Adapting to Distribution Shift by Visual Domain Prompt GenerationCode1
Discovering environments with XRMCode1
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate DomainsCode1
Diffusion Features to Bridge Domain Gap for Semantic SegmentationCode1
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent AlignmentCode1
Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning ParadigmCode1
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and TransferabilityCode1
DG-TTA: Out-of-domain Medical Image Segmentation through Augmentation and Descriptor-driven Domain Generalization and Test-Time AdaptationCode1
Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain DatasetsCode1
Show:102550
← PrevPage 3 of 36Next →

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
9MIRO (RegNetY-16GF, SWAD)Average Accuracy96.8Unverified
10CAR-FT (CLIP, ViT-B/16)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