Cover Image

OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fernández-Hernández, Alberto, Mestre, Jose I., Dolz, Manuel F., Duato, Jose, Quintana-Ortí, Enrique S.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FedOUI: OUI-Guided Client Weighting for Federated Aggregation
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

Sinusoidal Initialization, Time for a New Start
by: Fernández-Hernández, Alberto, et al.
Published: (2025)

FedSQ: Optimized Weight Averaging via Fixed Gating
by: Pérez-Corral, Cristian, et al.
Published: (2026)

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
by: Mestre, Jose I., et al.
Published: (2025)

Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training
by: Pérez-Corral, Cristian, et al.
Published: (2026)

Refresh-Scaling the Memory of Balanced Adam
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

$λ$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
by: Pérez-Corral, Cristian, et al.
Published: (2026)

StableGrad: Backward Scale Control without Batch Normalization
by: Mestre, Jose I., et al.
Published: (2026)

Why Adam Works Better with $β_1 = β_2$: The Missing Gradient Scale Invariance Principle
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

Detecting Atypical Clients in Federated Learning via Representation-Level Divergence
by: Pérez-Corral, Cristian, et al.
Published: (2026)

Overfitting in Histopathology Model Training: The Need for Customized Architectures
by: Alfasly, Saghir, et al.
Published: (2025)

Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
by: Beizaee, Farzad, et al.
Published: (2025)

SPARK: Stochastic Propagation via Affinity-guided Random walK for training-free unsupervised segmentation
by: Mahatha, Kunal, et al.
Published: (2026)

MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection
by: Beizaee, Farzad, et al.
Published: (2025)

Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection
by: Li, Yong, et al.
Published: (2025)

ORION: ORthonormal Text Encoding for Universal VLM AdaptatION
by: Chakraborty, Omprakash, et al.
Published: (2026)

Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation
by: Hajimiri, Sina, et al.
Published: (2024)

NERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation
by: Mahatha, Kunal, et al.
Published: (2025)

A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?
by: Silva-Rodríguez, Julio, et al.
Published: (2025)

Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation
by: Silva-Rodríguez, Julio, et al.
Published: (2023)

Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction
by: Silva-Rodríguez, Julio, et al.
Published: (2025)

Conformal Prediction for Zero-Shot Models
by: Silva-Rodríguez, Julio, et al.
Published: (2025)

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
by: Wang, Zhaoxin, et al.
Published: (2024)

All You Need to Know About Training Image Retrieval Models
by: Berton, Gabriele, et al.
Published: (2025)

ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training
by: Colussi, Marco, et al.
Published: (2024)

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models
by: Silva-Rodríguez, Julio, et al.
Published: (2023)

Class and Region-Adaptive Constraints for Network Calibration
by: Murugesan, Balamurali, et al.
Published: (2024)

Robust Calibration of Large Vision-Language Adapters
by: Murugesan, Balamurali, et al.
Published: (2024)

What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations
by: Liu, Dongqi, et al.
Published: (2025)

TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection
by: Xiong, Xinqi, et al.
Published: (2025)

SGPMIL: Sparse Gaussian Process Multiple Instance Learning
by: Lolos, Andreas, et al.
Published: (2025)

Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation
by: Murugesan, Balamurali, et al.
Published: (2023)

Calibrating Segmentation Networks with Margin-based Label Smoothing
by: Murugesan, Balamurali, et al.
Published: (2022)

Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation
by: Silva-Rodríguez, Julio, et al.
Published: (2025)

DART$^3$: Leveraging Distance for Test Time Adaptation in Person Re-Identification
by: Bhattacharya, Rajarshi, et al.
Published: (2025)

A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision
by: Silva-Rodríguez, Julio, et al.
Published: (2023)

Regularized Low-Rank Adaptation for Few-Shot Organ Segmentation
by: Baklouti, Ghassen, et al.
Published: (2025)