REVIEW 7 cited by
An Overview of Deep Semi-Supervised Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Deep neural networks demonstrated their ability to provide remarkable performances on a wide range of supervised learning tasks (e.g., image classification) when trained on extensive collections of labeled data (e.g., ImageNet). However, creating such large datasets requires a considerable amount of resources, time, and effort. Such resources may not be available in many practical cases, limiting the adoption and the application of many deep learning methods. In a search for more data-efficient deep learning methods to overcome the need for large annotated datasets, there is a rising research interest in semi-supervised learning and its applications to deep neural networks to reduce the amount of labeled data required, by either developing novel methods or adopting existing semi-supervised learning frameworks for a deep learning setting. In this paper, we provide a comprehensive overview of deep semi-supervised learning, starting with an introduction to the field, followed by a summarization of the dominant semi-supervised approaches in deep learning.
Forward citations
Cited by 7 Pith papers
-
Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
USP jointly improves unlabeled learning, memory stability, and plasticity in semi-supervised continual learning via feature-space reservation, divide-and-conquer pseudo-labeling, and class-mean distillation.
-
RAUM-Net: Regional Attention and Uncertainty-aware Mamba Network
RAUM-Net combines Mamba features, region attention, and MC-dropout uncertainty filtering to improve semi-supervised fine-grained classification under occlusion and label scarcity.
-
Adapting Under Fire: Multi-Agent Reinforcement Learning for Adversarial Drift in Network Security
The paper proposes a co-evolving red-blue reinforcement learning environment for network intrusion detection and claims the blue agent recovers up to 30% accuracy after just 2 to 3 adaptation steps with 25 to 30 sampl...
-
Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
ASAug uses entropy-adaptive rotation and translation as strong augmentations in a teacher-student consistency framework, improving semi-supervised semantic segmentation by 0.5 to 4 mIoU on three benchmarks.
-
Generative Data Augmentation for Object Point Cloud Segmentation
A mask-conditioned diffusion model generates labeled point cloud variants and filtered pseudo-labels, improving object part segmentation with only 10% hand labels.
-
Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning
A per-image positive-unlabeled classifier adds extra background pseudo-labels in semi-supervised medical segmentation, giving modest average Dice gains.
-
Reinforcement Learning: From Algorithms To Foundation Models
A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.
Discussion (0). Continue with ORCID to comment.