SOTAVerified

Domain Adaptation

Domain Adaptation is the task of adapting models across domains. This is motivated by the challenge where the test and training datasets fall from different data distributions due to some factor. Domain adaptation aims to build machine learning models that can be generalized into a target domain and dealing with the discrepancy across domain distributions.

Further readings:

( Image credit: Unsupervised Image-to-Image Translation Networks )

Papers

Showing 47514800 of 6439 papers

TitleStatusHype
Measuring the Feasibility of Analogical Transfer using Complexity0
MedAI at SemEval-2021 Task 10: Negation-aware Pre-training for Source-free Negation Detection Domain Adaptation0
MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder0
MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment0
MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection0
Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation0
Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation0
Memory Efficient Temporal & Visual Graph Model for Unsupervised Video Domain Adaptation0
Meta-hallucinator: Towards Few-Shot Cross-Modality Cardiac Image Segmentation0
Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation0
Meta-Learning across Meta-Tasks for Few-Shot Learning0
Meta-Learning for Few-Shot NMT Adaptation0
Meta-Learning with Domain Adaptation for Few-Shot Learning under Domain Shift0
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning0
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions0
Meta-Reinforced Multi-Domain State Generator for Dialogue Systems0
Meta Reinforcement Learning for Sim-to-real Domain Adaptation0
MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation0
Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification0
Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training0
Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning0
Metric-Learning-Assisted Domain Adaptation0
Metric Learning for Graph-Based Domain Adaptation0
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation0
MI^2GAN: Generative Adversarial Network for Medical Image Domain Adaptation using Mutual Information Constraint0
MIAdapt: Source-free Few-shot Domain Adaptive Object Detection for Microscopic Images0
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation0
MICE: a middleware layer for MT0
MiDAS: Multi-integrated Domain Adaptive Supervision for Fake News Detection0
MiddleGAN: Generate Domain Agnostic Samples for Unsupervised Domain Adaptation0
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking0
Mind the Discriminability: Asymmetric Adversarial Domain Adaptation0
Mind the Gap: Subspace based Hierarchical Domain Adaptation0
Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets0
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation0
Minimax Statistical Learning with Wasserstein Distances0
Minimizing Energy Costs in Deep Learning Model Training: The Gaussian Sampling Approach0
Mining Label Distribution Drift in Unsupervised Domain Adaptation0
Min-Max Statistical Alignment for Transfer Learning0
MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond0
Mirror Sample Based Distribution Alignment for Unsupervised Domain Adaption0
MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation0
Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling0
Mitigating Domain Mismatch in Face Recognition Using Style Matching0
Mitigating domain shift in AI-based tuberculosis screening with unsupervised domain adaptation0
Mitigating Receiver Impact on Radio Frequency Fingerprint Identification via Domain Adaptation0
Mitigating the Impact of Electrode Shift on Classification Performance in Electromyography-Based Motion Prediction Using Sliding-Window Normalization0
Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model0
Mitigating the Influence of Domain Shift in Skin Lesion Classification: A Benchmark Study of Unsupervised Domain Adaptation Methods on Dermoscopic Images0
Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation0
Show:102550
← PrevPage 96 of 129Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FFTATAverage Accuracy96Unverified
2PMTransAverage Accuracy95.3Unverified
3CMKDAverage Accuracy94.4Unverified
4SSRT-B (ours)Average Accuracy93.5Unverified
5CDTransAverage Accuracy92.6Unverified
6CoViAverage Accuracy91.8Unverified
7GSDEAverage Accuracy91.7Unverified
8FixBiAverage Accuracy91.4Unverified
9Contrastive Adaptation NetworkAverage Accuracy90.6Unverified
10BIWAAAverage Accuracy90.5Unverified
#ModelMetricClaimedVerifiedStatus
1HALOmIoU78.1Unverified
2ILM-ASSLmIoU76.6Unverified
3DCFmIoU69.3Unverified
4HRDA+PiPamIoU68.2Unverified
5MICmIoU67.3Unverified
6FREDOM - TransformermIoU67Unverified
7HRDAmIoU65.8Unverified
8SePiComIoU64.3Unverified
9MIC + Guidance TrainingmIoU63.8Unverified
10DAFormer + ProCSTmIoU61.6Unverified
#ModelMetricClaimedVerifiedStatus
1HALOmIoU77.8Unverified
2DCFmIoU77.7Unverified
3ILM-ASSLmIoU76.1Unverified
4MICmIoU75.9Unverified
5HRDA+PiPamIoU75.6Unverified
6HRDAmIoU73.8Unverified
7FREDOM - TransformermIoU73.6Unverified
8HALOmIoU73.3Unverified
9SePiComIoU70.3Unverified
10DAFormer + ProCSTmIoU69.4Unverified
#ModelMetricClaimedVerifiedStatus
1SWGAccuracy92.3Unverified
2RCLAccuracy90Unverified
3PGA (ViT-L/14)Accuracy89.4Unverified
4CMKDAccuracy89Unverified
5PMTransAccuracy89Unverified
6MICAccuracy86.2Unverified
7PGA (ViT-B/16)Accuracy85.1Unverified
8ELSAccuracy84.6Unverified
9SDAT (ViT-B/16)Accuracy84.3Unverified
10CDTrans (DeiT-B)Accuracy80.5Unverified
#ModelMetricClaimedVerifiedStatus
1FFTATAccuracy93.8Unverified
2RCLAccuracy93.2Unverified
3MICAccuracy92.8Unverified
4SWGAccuracy92.7Unverified
5CMKDAccuracy91.8Unverified
6DePTAccuracy90.7Unverified
7SDAT(ViT)Accuracy89.8Unverified
8SFDA2++Accuracy89.6Unverified
9PMtransAccuracy88.8Unverified
10CoViAccuracy88.5Unverified
#ModelMetricClaimedVerifiedStatus
1CMKDAccuracy94.3Unverified
2MCC+NWDAccuracy90.7Unverified
3GLOT-DRAccuracy90.4Unverified
4SPLAccuracy90.3Unverified
5DFA-SAFNAccuracy90.2Unverified
6DADAAccuracy89.3Unverified
7DFA-ENTAccuracy89.1Unverified
8DDAAccuracy88.9Unverified
9MEDMAccuracy88.9Unverified
10IAFN+ENTAccuracy88.9Unverified
#ModelMetricClaimedVerifiedStatus
1SoRAmIoU78.8Unverified
2ReinmIoU77.6Unverified
3CoDAmIoU72.6Unverified
4Refign (HRDA)mIoU72.1Unverified
5HALOmIoU71.9Unverified
6MICmIoU70.4Unverified
7HRDAmIoU68Unverified
8Refign (DAFormer)mIoU65.5Unverified
9VBLC (DAFormer)mIoU64.2Unverified
10CMFormermIoU60.1Unverified
#ModelMetricClaimedVerifiedStatus
1FACTAccuracy98.8Unverified
2FAMCDAccuracy98.72Unverified
3DFA-MCDAccuracy98.6Unverified
4Mean teacherAccuracy98.26Unverified
5DRANetAccuracy98.2Unverified
6SHOTAccuracy98Unverified
7DFA-ENTAccuracy97.9Unverified
8CyCleGAN (Light-weight Calibrator)Accuracy97.1Unverified