Cover Image

From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gabetni, Firas, Henry, Alexandre Rocchi, Belkhir, Nacim, Liu, Ziyi, Franchi, Gianni
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Geometric Unification of Concept Learning with Concept Cones
by: Rocchi--Henry, Alexandre, et al.
Published: (2025)

Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
by: Franchi, Gianni, et al.
Published: (2024)

NECO: NEural Collapse Based Out-of-distribution detection
by: Ammar, Mouïn Ben, et al.
Published: (2023)

Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
by: Gabetni, Firas, et al.
Published: (2025)

Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning
by: Yamane, Takehiro, et al.
Published: (2025)

FakeParts: a New Family of AI-Generated DeepFakes
by: Liu, Ziyi, et al.
Published: (2025)

Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
by: Lafage, Adrien, et al.
Published: (2025)

PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision
by: Wang, Chengjie, et al.
Published: (2024)

Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation
by: Hoche, Joseph, et al.
Published: (2026)

Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift
by: Goksu, Ozgu, et al.
Published: (2024)

Foundation Models and Transformers for Anomaly Detection: A Survey
by: Ammar, Mouïn Ben, et al.
Published: (2025)

Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
by: Liu, Ziyi, et al.
Published: (2025)

Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
by: Kazmierczak, Rémi, et al.
Published: (2025)

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
by: Xia, Guoxuan, et al.
Published: (2024)

Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
by: Li, Wangkai, et al.
Published: (2025)

When Imbalance Comes Twice: Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation
by: Combes, Julien, et al.
Published: (2026)

Learning to Generate Training Datasets for Robust Semantic Segmentation
by: Hariat, Marwane, et al.
Published: (2023)

Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Data
by: Zhang, Jie, et al.
Published: (2024)

Domain Generalisation for Object Detection under Covariate and Concept Shift
by: Seemakurthy, Karthik, et al.
Published: (2022)

CLIP-QDA: An Explainable Concept Bottleneck Model
by: Kazmierczak, Rémi, et al.
Published: (2023)

Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting
by: Lafage, Adrien, et al.
Published: (2024)

SS3D: End2End Self-Supervised 3D from Web Videos
by: Hariat, Marwane, et al.
Published: (2026)

Explainability for Vision Foundation Models: A Survey
by: Kazmierczak, Rémi, et al.
Published: (2025)

PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecasting
by: Xu, Yihong, et al.
Published: (2024)

RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction
by: Künzel, Johannes, et al.
Published: (2025)

Detecting Media Clones in Cultural Repositories Using a Positive Unlabeled Learning Approach
by: Sevetlidis, V., et al.
Published: (2026)

POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization
by: Vahdani, Elahe, et al.
Published: (2023)

Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift
by: Achara, Akshit, et al.
Published: (2026)

Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels
by: Tian, Yuxin, et al.
Published: (2024)

UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition
by: Ghilotti, Filippo, et al.
Published: (2026)

PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning
by: Liu, Xiaoyu, et al.
Published: (2024)

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction
by: Zhang, Quan, et al.
Published: (2025)

Smooth Pseudo-Labeling
by: Karaliolios, Nikolaos, et al.
Published: (2024)

Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning
by: Saravanan, Darshana, et al.
Published: (2024)

Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
by: Dünkel, Olaf, et al.
Published: (2025)

Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
by: Rakotoarivony, Lucas
Published: (2025)

Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
by: Feng, Qianhan, et al.
Published: (2024)

InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
by: Huang, Zhe, et al.
Published: (2024)

LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
by: Si, Haozhe, et al.
Published: (2026)

Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition
by: Haliassos, Alexandros, et al.
Published: (2026)