SOTAVerified|Agents Browse Leaderboard About

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

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1151–1160 of 1751 papers

Title	Date	Tasks	Status	Hype
On Invariance Penalties for Risk Minimization	Jun 17, 2021	Domain Generalization	—Unverified	0
On Inverse Problems, Parameter Estimation, and Domain Generalization	Jun 6, 2025	DeblurringDomain Generalization	—Unverified	0
On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources	Nov 27, 2021	Domain AdaptationDomain Generalization	—Unverified	0
On the benefits of representation regularization in invariance based domain generalization	May 30, 2021	Domain GeneralizationRepresentation Learning	—Unverified	0
On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation	Sep 15, 2021	Domain AdaptationDomain Generalization	—Unverified	0
On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation	Oct 16, 2021	Domain AdaptationDomain Generalization	—Unverified	0
On the Consideration of AI Openness: Can Good Intent Be Abused?	Mar 11, 2024	Domain Generalization	—Unverified	0
On the Generalization of Handwritten Text Recognition Models	Nov 26, 2024	Domain AdaptationDomain Generalization	—Unverified	0
On the Generalization Properties of Deep Learning for Aircraft Fuel Flow Estimation Models	Oct 10, 2024	Domain Generalization	—Unverified	0
On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space	Feb 23, 2023	Binary ClassificationDomain Adaptation	—Unverified	0

Show:10 25 50

← PrevPage 116 of 176Next →

All datasets PACS VizWiz-Classification ImageNet-C Office-Home ImageNet-A ImageNet-R DomainNet VLCS TerraIncognita GTA-to-Avg(Cityscapes,BDD,Mapillary)ImageNet-Sketch GTA5 to Cityscapes

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SIMPLE+	Average Accuracy	99	—	Unverified
2	PromptStyler (CLIP, ViT-L/14)	Average Accuracy	98.6	—	Unverified
3	GMDG (RegNetY-16GF, SWAD)	Average Accuracy	97.9	—	Unverified
4	D-Triplet(RegNetY-16GF)	Average Accuracy	97.6	—	Unverified
5	MoA (OpenCLIP, ViT-B/16)	Average Accuracy	97.4	—	Unverified
6	GMDG (e RegNetY-16GF)	Average Accuracy	97.3	—	Unverified
7	PromptStyler (CLIP, ViT-B/16)	Average Accuracy	97.2	—	Unverified
8	SPG (CLIP, ViT-B/16)	Average Accuracy	97	—	Unverified
9	CAR-FT (CLIP, ViT-B/16)	Average Accuracy	96.8	—	Unverified
10	MIRO (RegNetY-16GF, SWAD)	Average Accuracy	96.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ViT-8/B-224	Accuracy - Clean Images	450	—	Unverified
2	VOLO-D5	Accuracy - All Images	57.2	—	Unverified
3	ConvNeXt-B	Accuracy - All Images	53.5	—	Unverified
4	ResNeXt-101 32x16d	Accuracy - All Images	51.7	—	Unverified
5	EfficientNet-B8 (advprop+autoaug)	Accuracy - All Images	50.5	—	Unverified
6	EfficientNet-B7 (advprop+autoaug)	Accuracy - All Images	49.7	—	Unverified
7	EfficientNet-B6 (advprop+autoaug)	Accuracy - All Images	49.6	—	Unverified
8	EfficientNet-B5 (advprop+autoaug)	Accuracy - All Images	49.1	—	Unverified
9	ViT-16/L-224	Accuracy - All Images	49	—	Unverified
10	ResNet-50 (gn)	Accuracy - All Images	48.9	—	Unverified