DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
hub
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
representative citing papers
OVS-DINO structurally aligns DINO with SAM to revitalize attenuated boundary features, achieving SOTA gains of 2.1% average and 6.3% on Cityscapes in weakly-supervised open-vocabulary segmentation.
PolarMAE is a new unsupervised pre-training method for fetal ultrasound that uses progressive visual-semantic screening, acoustic-bounded constraints, and polar-texture masking to reach state-of-the-art performance on downstream interpretation tasks.
Membership inference attacks can detect whether specific ECG data participated in pretraining self-supervised foundation encoders, with leakage strongest in small cohorts and contrastive models.
DART mitigates structural overfitting in graph missing-feature imputation via global structural augmentation, masked-autoencoder semantic rectification, and test-time distribution rectification, outperforming prior methods on transductive and inductive tasks including a new real-missing dataset.
GenPAS unifies common data augmentation strategies for generative recommendation as special cases of a bias-controlled stochastic sampling process and demonstrates gains in accuracy, data efficiency, and parameter efficiency on benchmarks and industrial data.
LeNEPA proposes a no-augmentation next-latent prediction recipe that maintains frozen-probe performance across ECG and synthetic diagnostic time-series datasets under fixed-recipe conditions where a tuned JEPA baseline degrades.
MAEPose is a self-supervised masked autoencoder operating on mmWave spectrogram videos that learns motion representations and decodes multi-frame poses, outperforming baselines by up to 22.1% MPJPE.
citing papers explorer
-
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
-
OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
OVS-DINO structurally aligns DINO with SAM to revitalize attenuated boundary features, achieving SOTA gains of 2.1% average and 6.3% on Cityscapes in weakly-supervised open-vocabulary segmentation.
-
PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking
PolarMAE is a new unsupervised pre-training method for fetal ultrasound that uses progressive visual-semantic screening, acoustic-bounded constraints, and polar-texture masking to reach state-of-the-art performance on downstream interpretation tasks.
-
Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders
Membership inference attacks can detect whether specific ECG data participated in pretraining self-supervised foundation encoders, with leakage strongest in small cohorts and contrastive models.
-
Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
DART mitigates structural overfitting in graph missing-feature imputation via global structural augmentation, masked-autoencoder semantic rectification, and test-time distribution rectification, outperforming prior methods on transductive and inductive tasks including a new real-missing dataset.
-
Sequential Data Augmentation for Generative Recommendation
GenPAS unifies common data augmentation strategies for generative recommendation as special cases of a bias-controlled stochastic sampling process and demonstrates gains in accuracy, data efficiency, and parameter efficiency on benchmarks and industrial data.
-
LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
LeNEPA proposes a no-augmentation next-latent prediction recipe that maintains frozen-probe performance across ECG and synthetic diagnostic time-series datasets under fixed-recipe conditions where a tuned JEPA baseline degrades.
-
MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video
MAEPose is a self-supervised masked autoencoder operating on mmWave spectrogram videos that learns motion representations and decodes multi-frame poses, outperforming baselines by up to 22.1% MPJPE.
- Latent Denoising Improves Visual Alignment in Large Multimodal Models
- Bridging the Micro--Macro Gap: Frequency-Aware Semantic Alignment for Image Manipulation Localization