Copertina

Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mots'oehli, Moseli, Mogale, Hope, Baek, Kyungim
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise
di: Mots'oehli, Moseli, et al.
Pubblicazione: (2024)

Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review
di: Mots'oehli, Moseli
Pubblicazione: (2024)

Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception
di: Mots'oehli, Moseli, et al.
Pubblicazione: (2025)

FishNet: Deep Neural Networks for Low-Cost Fish Stock Estimation
di: Mots'oehli, Moseli, et al.
Pubblicazione: (2024)

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

Balancing Accuracy and Efficiency: CNN Fusion Models for Diabetic Retinopathy Screening
di: Islam, Md Rafid, et al.
Pubblicazione: (2025)

CALICO: Confident Active Learning with Integrated Calibration
di: Querol, Lorenzo S., et al.
Pubblicazione: (2024)

FairNVT: Improving Fairness via Noise Injection in Vision Transformers
di: Tang, Qiaoyue, et al.
Pubblicazione: (2026)

Scaling Semantic Categories: Investigating the Impact on Vision Transformer Labeling Performance
di: Lamelas, Anthony, et al.
Pubblicazione: (2025)

NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
di: Xu, Jiayu, et al.
Pubblicazione: (2026)

LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
di: Mehri, Faridoun, et al.
Pubblicazione: (2024)

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
di: Olszewski, Jan, et al.
Pubblicazione: (2023)

Gaze-Informed Vision Transformers: Predicting Driving Decisions Under Uncertainty
di: Koorathota, Sharath, et al.
Pubblicazione: (2023)

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation
di: Lee, Taeckyung, et al.
Pubblicazione: (2024)

A Conformal Prediction Score that is Robust to Label Noise
di: Penso, Coby, et al.
Pubblicazione: (2024)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
di: Chen, Hao, et al.
Pubblicazione: (2023)

PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation
di: Ranzinger, Mike, et al.
Pubblicazione: (2024)

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2024)

From Theory to Decision Rule: Calibrating the Noisy-Label Crossover for Vision-Language Model Weak Supervision Across Three Medical-Imaging Benchmarks
di: Xu, Bruce Changlong, et al.
Pubblicazione: (2026)

Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated
di: Yang, Muli, et al.
Pubblicazione: (2026)

Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
di: Geng, Zibin, et al.
Pubblicazione: (2026)

Balancing Accuracy and Training Time in Federated Learning for Violence Detection in Surveillance Videos: A Study of Neural Network Architectures
di: Quentin, Pajon, et al.
Pubblicazione: (2023)

Continual Adaptation of Vision Transformers for Federated Learning
di: Halbe, Shaunak, et al.
Pubblicazione: (2023)

FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
di: Ye, Mengwen, et al.
Pubblicazione: (2025)

Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
di: Dereka, Stanislav, et al.
Pubblicazione: (2023)

Effortless Active Labeling for Long-Term Test-Time Adaptation
di: Wang, Guowei, et al.
Pubblicazione: (2025)

From Ground to Air: Noise Robustness in Vision Transformers and CNNs for Event-Based Vehicle Classification with Potential UAV Applications
di: Almesafri, Nouf, et al.
Pubblicazione: (2025)

Combating Semantic Contamination in Learning with Label Noise
di: Fan, Wenxiao, et al.
Pubblicazione: (2024)

Margin and Consistency Supervision for Calibrated and Robust Vision Models
di: Khazem, Salim
Pubblicazione: (2026)

Convolutional Neural Nets vs Vision Transformers: A SpaceNet Case Study with Balanced vs Imbalanced Regimes
di: Gothi, Akshar
Pubblicazione: (2025)

A Survey of the Self Supervised Learning Mechanisms for Vision Transformers
di: Khan, Asifullah, et al.
Pubblicazione: (2024)

Pre-training Vision Transformers with Formula-driven Supervised Learning
di: Kataoka, Hirokatsu, et al.
Pubblicazione: (2022)

Beyond Generation: Multi-Hop Reasoning for Factual Accuracy in Vision-Language Models
di: Hossain, Shamima
Pubblicazione: (2025)

Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
di: Yu, Geng, et al.
Pubblicazione: (2024)

Improving Multi-Label Contrastive Learning by Leveraging Label Distribution
di: Chen, Ning, et al.
Pubblicazione: (2025)

Granular-ball Representation Learning for Deep CNN on Learning with Label Noise
di: Dai, Dawei, et al.
Pubblicazione: (2024)

Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
di: Chen, Hao, et al.
Pubblicazione: (2023)

Adapting Vision-Language Models Without Labels: A Comprehensive Survey
di: Dong, Hao, et al.
Pubblicazione: (2025)

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
di: Wu, Fang, et al.
Pubblicazione: (2026)

AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network
di: Kang, Donghwa, et al.
Pubblicazione: (2024)