Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goel, Atharv, Agarwal, Sharat, Anand, Saket, Arora, Chetan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
by: Jindal, Akshit, et al.
Published: (2026)

Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces
by: Sani, Depanshu, et al.
Published: (2025)

ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
by: Patni, Suraj, et al.
Published: (2024)

Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
by: Peng, Ningkang, et al.
Published: (2026)

Exploiting Contextual Uncertainty of Visual Data for Efficient Training of Deep Models
by: Agarwal, Sharat
Published: (2024)

Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop
by: Goel, Atharv, et al.
Published: (2025)

Prompting without Panic: Attribute-aware, Zero-shot, Test-Time Calibration
by: Hebbalaguppe, Ramya, et al.
Published: (2025)

Information Geometry of Evolution of Neural Network Parameters While Training
by: Thiruthummal, Abhiram Anand, et al.
Published: (2024)

Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR
by: Vempati, Shashank, et al.
Published: (2025)

Feature Space Perturbation: A Panacea to Enhanced Transferability Estimation
by: Khoba, Prafful Kumar, et al.
Published: (2025)

Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
by: Raj, Ankita, et al.
Published: (2025)

Examining the Threat Landscape: Foundation Models and Model Stealing
by: Raj, Ankita, et al.
Published: (2025)

Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
by: Koromilas, Panagiotis, et al.
Published: (2026)

Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling
by: Lyu, Zongyao, et al.
Published: (2024)

Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
by: Yang, Peiyu, et al.
Published: (2026)

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
by: Peng, Ningkang, et al.
Published: (2026)

Scalable Class-Incremental Learning Based on Parametric Neural Collapse
by: Zhang, Chuangxin, et al.
Published: (2025)

Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
by: Wang, Yining, et al.
Published: (2024)

All-around Neural Collapse for Imbalanced Classification
by: Zhang, Enhao, et al.
Published: (2024)

TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations
by: Siampou, Maria Despoina, et al.
Published: (2026)

Exploiting Label Skewness for Spiking Neural Networks in Federated Learning
by: Yu, Di, et al.
Published: (2024)

Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score
by: Khan, Abdullah Ahmad, et al.
Published: (2026)

From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
by: Gabetni, Firas, et al.
Published: (2026)

Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
by: Arteaga, Gabriel Y., et al.
Published: (2025)

MaxSup: Overcoming Representation Collapse in Label Smoothing
by: Zhou, Yuxuan, et al.
Published: (2025)

Geometry-Informed Neural Networks
by: Berzins, Arturs, et al.
Published: (2024)

Memory-efficient Continual Learning with Neural Collapse Contrastive
by: Dang, Trung-Anh, et al.
Published: (2024)

BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse
by: Wang, Yuanchao, et al.
Published: (2025)

Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling
by: Sani, Depanshu, et al.
Published: (2025)

Shortcut Learning Susceptibility in Vision Classifiers
by: Suhail, Pirzada, et al.
Published: (2025)

Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
by: Wu, Yingwen, et al.
Published: (2024)

Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise
by: Khanal, Bidur, et al.
Published: (2024)

Learning from True-False Labels via Multi-modal Prompt Retrieving
by: Li, Zhongnian, et al.
Published: (2024)

Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold
by: Jin, Yinzhu, et al.
Published: (2024)

To Label or Not to Label: PALM -- A Predictive Model for Evaluating Sample Efficiency in Active Learning Models
by: Machnio, Julia, et al.
Published: (2025)

Reliable Student: Addressing Noise in Semi-Supervised 3D Object Detection
by: Nozarian, Farzad, et al.
Published: (2024)

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
by: He, Chiyuan, et al.
Published: (2026)

Counting Network for Learning from Majority Label
by: Shiku, Kaito, et al.
Published: (2024)

ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory
by: Wang, Jianchao, et al.
Published: (2025)

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