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 110 of 1751 papers

TitleStatusHype
MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modeling0
GLAD: Generalizable Tuning for Vision-Language Models0
Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain GeneralizationCode0
InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofingCode1
From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion0
Integrated Structural Prompt Learning for Vision-Language Models0
Feed-Forward SceneDINO for Unsupervised Semantic Scene CompletionCode2
Prompt-Free Conditional Diffusion for Multi-object Image AugmentationCode1
Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations0
Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization0
Show:102550
← PrevPage 1 of 176Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet-50mean Corruption Error (mCE)76.7Unverified
2Group-wise Inhibition (ResNet-50)mean Corruption Error (mCE)69.6Unverified
3Stylized ImageNet (ResNet-50)mean Corruption Error (mCE)69.3Unverified
4AugMix (ResNet-50)mean Corruption Error (mCE)65.3Unverified
5APR-SP (ResNet-50)mean Corruption Error (mCE)65Unverified
6DiffAUD (ConvNeXt-Tiny)Top 1 Accuracy64.3Unverified
7DiffAUD (Swin-Tiny)Top 1 Accuracy61Unverified
8DeepAugment (ResNet-50)mean Corruption Error (mCE)60.4Unverified
9PRIME (ResNet-50)mean Corruption Error (mCE)57.5Unverified
10APR-SP + DeepAugment (ResNet-50)mean Corruption Error (mCE)57.5Unverified