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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 1751 papers

TitleStatusHype
Generalized Trajectory Scoring for End-to-end Multimodal PlanningCode3
On Inverse Problems, Parameter Estimation, and Domain Generalization—0
UniPTMs: The First Unified Multi-type PTM Site Prediction Model via Master-Slave Architecture-Based Multi-Stage Fusion Strategy and Hierarchical Contrastive LossCode0
Learning Beyond Experience: Generalizing to Unseen State Space with Reservoir ComputingCode0
VUDG: A Dataset for Video Understanding Domain Generalization—0
A Flat Minima Perspective on Understanding Augmentations and Model Robustness—0
RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget—0
Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction—0
Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts—0
Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain GeneralizationCode0
Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive LearningCode0
IRS: Incremental Relationship-guided Segmentation for Digital PathologyCode0
Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains—0
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models—0
LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image SegmentationCode1
Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding—0
Dual-Path Stable Soft Prompt Generation for Domain Generalization—0
Distilling LLM Agent into Small Models with Retrieval and Code ToolsCode3
CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-AttentionCode0
Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPOCode4
Single Domain Generalization for Few-Shot Counting via Universal Representation MatchingCode0
Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces—0
Trends and Challenges in Authorship Analysis: A Review of ML, DL, and LLM Approaches—0
Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation—0
Show:102550
← PrevPage 2 of 71Next →
All datasetsPACSVizWiz-ClassificationImageNet-COffice-HomeImageNet-AImageNet-RDomainNetVLCSTerraIncognitaGTA-to-Avg(Cityscapes,BDD,Mapillary)ImageNet-SketchGTA5 to Cityscapes

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SIMPLE+Average Accuracy99—Unverified
2PromptStyler (CLIP, ViT-L/14)Average Accuracy98.6—Unverified
3GMDG (RegNetY-16GF, SWAD)Average Accuracy97.9—Unverified
4D-Triplet(RegNetY-16GF)Average Accuracy97.6—Unverified
5MoA (OpenCLIP, ViT-B/16)Average Accuracy97.4—Unverified
6GMDG (e RegNetY-16GF)Average Accuracy97.3—Unverified
7PromptStyler (CLIP, ViT-B/16)Average Accuracy97.2—Unverified
8SPG (CLIP, ViT-B/16)Average Accuracy97—Unverified
9CAR-FT (CLIP, ViT-B/16)Average Accuracy96.8—Unverified
10MIRO (RegNetY-16GF, SWAD)Average Accuracy96.8—Unverified
#ModelMetricClaimedVerifiedStatus
1ViT-8/B-224Accuracy - Clean Images450—Unverified
2VOLO-D5Accuracy - All Images57.2—Unverified
3ConvNeXt-BAccuracy - All Images53.5—Unverified
4ResNeXt-101 32x16dAccuracy - All Images51.7—Unverified
5EfficientNet-B8 (advprop+autoaug)Accuracy - All Images50.5—Unverified
6EfficientNet-B7 (advprop+autoaug)Accuracy - All Images49.7—Unverified
7EfficientNet-B6 (advprop+autoaug)Accuracy - All Images49.6—Unverified
8EfficientNet-B5 (advprop+autoaug)Accuracy - All Images49.1—Unverified
9ViT-16/L-224Accuracy - All Images49—Unverified
10ResNet-50 (gn)Accuracy - All Images48.9—Unverified