GGR is a gradient-space projection technique that rectifies auxiliary updates in open-set SSL to avoid first-order opposition with supervised learning while retaining orthogonal signals.
arXiv preprint arXiv:1911.09785 (2019)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
A teacher–student semi-supervised framework with alignment-preserving patch mixing, position-aware text augmentation, and positional contrastive learning improves medical referring segmentation at low label ratios.
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
UGEL employs deep beta regression to estimate uncertainty in one forward pass, enabling faster convergence in edge learning for remote sensing image regression than active or semi-supervised baselines.
citing papers explorer
-
Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
GGR is a gradient-space projection technique that rectifies auxiliary updates in open-set SSL to avoid first-order opposition with supervised learning while retaining orthogonal signals.
-
Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment
A teacher–student semi-supervised framework with alignment-preserving patch mixing, position-aware text augmentation, and positional contrastive learning improves medical referring segmentation at low label ratios.
-
Revisiting Feature Prediction for Learning Visual Representations from Video
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
-
Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing
UGEL employs deep beta regression to estimate uncertainty in one forward pass, enabling faster convergence in edge learning for remote sensing image regression than active or semi-supervised baselines.
- SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data