Semi-Supervised Learning

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 175% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 128

All topics

Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
Dec 11, 2025Tian Liu, Anwesha Basu, James Caverlee +1Few-Shot Learning Vision-Language Model Adaptation
Texas A&M University · University of Macau · Institute of Collaborative Innovation
A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees
Nov 28, 2025Miao Zhang, Junpeng Li, Changchun Hua +1Empirical Risk Minimization Semi-Supervised Learning
Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment, Yanshan University, Qinhuangdao, China
Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies
Nov 5, 2025Gaia Grosso, Sai Sumedh R. Hindupur, Thomas Fel +3Graph Anomaly Detection Abnormality
NSF AI Institute for Artificial Intelligence and Fundamental Interactions, Cambridge, 02139, MA · Laboratory for Nuclear Science, Massachusetts Institute of Technology, Cambridge, 02139, MA · School of Engineering and Applied Sciences, Harvard University, Allston, 02134, MA +1
Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling
Oct 10, 2025Haroon Gharwi, Yue Dai, Kai ShuRecurrent Neural Networks Conditional Variational Autoencoder
Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA · Department of Computer Science, Emory University, Atlanta, GA, USA
Beyond Correlation: Learning Supervised, Sample-Distinct, and Eigenimage-Interpretable Representations
Jul 22, 2025Mojtaba MoattariDimensionality Reduction Face Recognition Model
Independent Researcher
An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression
Apr 25, 2025Christopher Bülte, Yusuf Sale, Timo Löhr +3Uncertainty Quantification Uncertainty
1LMU Munich · 2Munich Center for Machine Learning (MCML) · 3DLR-German Aerospace Center +2
Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training
Apr 2, 2025Luca Ciampi, Gabriele Lagani, Giuseppe Amato +1Semi-Supervised Medical Image Segmentation Semi-Supervised Learning
ISTI-CNR, Pisa, Italy
The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms
Nov 18, 2024Samir M. Perlaza, Xinying ZouGeneralization Bounds Empirical Risk Minimization
INRIA, Centre Inria d’Universit´e Cˆote d’Azur, 06902 Sophia Antipolis, France

Dec 11, 2025, cs.CVJ/K move · Enter open · S save

Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective

Tian Liu, Anwesha Basu, James Caverlee, Shu Kong

Texas A&M University · University of Macau · Institute of Collaborative Innovation

Few-Shot Learning Vision-Language Model Adaptation Semi-Supervised Learning Supervised Finetuning Unlabeled Data Recent Vision-Language Models+1

Open paper AskPDF arXiv

Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled and abundant unlabeled task-specific examples to annotate the unlabeled ones. Despite the availability of powerful open-source Vision-Language Models (VLMs) and open-world data, existing SSFSL literature largely neglects these resources. In contrast, the related area few-shot learning (FSL) has already exploited them to boost performance. Arguably, to solve real-world auto-annotation, SSFSL should leverage such open resources. To bridge this gap, we explore established SSL methods to finetune a VLM. Unexpectedly, they significantly underperform FSL baselines that do not use unlabeled data. Our in-depth analysis reveals the root cause of failure: VLMs produce flat distributions of softmax probabilities, resulting in zero utilization of unlabeled data and weak supervision signals. To address this challenge, we propose an embarrassingly simple solution that uses temperatures to sharpen the softmax output, which not only increases the confidence scores of pseudo-labels to improve the utilization of unlabeled data, but also strengthens training supervision for effective finetuning. Furthermore, we exploit task-relevant open data, e.g., those retrieved from VLMs' publicly available pretraining set. To mitigate the imbalance and domain gaps in retrieved data, we employ a stage-wise training strategy. Building on the successful finetuning of VLMs and the exploitation of open data, we present a simple yet effective SSFSL method, Stage-Wise Finetuning with Temperatures (SWIFT). Across five benchmarks, SWIFT outperforms recent FSL and SSL methods by

\sim

5 accuracy points. SWIFT even rivals supervised learning, which finetunes a VLM assuming unlabeled data having ground-truth labels!

Momentum

Related topics

Latest papers 128