Image de couverture de livre

Revisiting Mixout: An Overlooked Path to Robust Finetuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Aminbeidokhti, Masih, Medeiros, Heitor Rapela, Granger, Eric, Pedersoli, Marco
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
par: Aminbeidokhti, Masih, et autres
Publié: (2025)

Domain Generalization by Rejecting Extreme Augmentations
par: Aminbeidokhti, Masih, et autres
Publié: (2023)

Source-Free Domain Adaptation for YOLO Object Detection
par: Varailhon, Simon, et autres
Publié: (2024)

Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
par: Medeiros, Heitor Rapela, et autres
Publié: (2024)

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
par: Aminbeidokhti, Masih, et autres
Publié: (2025)

WiSE-OD: Benchmarking Robustness in Infrared Object Detection
par: Medeiros, Heitor R., et autres
Publié: (2025)

Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?
par: Muralidharan, Srikanth, et autres
Publié: (2025)

HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
par: Medeiros, Heitor Rapela, et autres
Publié: (2023)

Visual Modality Prompt for Adapting Vision-Language Object Detectors
par: Medeiros, Heitor R., et autres
Publié: (2024)

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
par: Fournier, Louis, et autres
Publié: (2024)

VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
par: Belal, Atif, et autres
Publié: (2025)

MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection
par: Medeiros, Heitor R., et autres
Publié: (2024)

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
par: Murtaza, Shakeeb, et autres
Publié: (2024)

Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
par: Murtaza, Shakeeb, et autres
Publié: (2024)

TeD-Loc: Text Distillation for Weakly Supervised Object Localization
par: Murtaza, Shakeeb, et autres
Publié: (2025)

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
par: Belal, Atif, et autres
Publié: (2024)

Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition
par: Belharbi, Soufiane, et autres
Publié: (2024)

BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change
par: González-González, Manuela, et autres
Publié: (2025)

Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
par: Liu, Haoyang, et autres
Publié: (2024)

Joint Multimodal Transformer for Emotion Recognition in the Wild
par: Waligora, Paul, et autres
Publié: (2024)

Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition
par: Aslam, Muhammad Haseeb, et autres
Publié: (2024)

Do not trust what you trust: Miscalibration in Semi-supervised Learning
par: Mishra, Shambhavi, et autres
Publié: (2024)

Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification
par: Nehdi, Taha Mustapha, et autres
Publié: (2025)

Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues
par: Belharbi, Soufiane, et autres
Publié: (2024)

Masked Multi-Query Slot Attention for Unsupervised Object Discovery
par: Pramanik, Rishav, et autres
Publié: (2024)

TRACER: Persistent Regularization for Robust Multimodal Finetuning
par: Asadollahzadeh, Hesam, et autres
Publié: (2026)

Task Matrices: Linear Maps for Cross-Model Finetuning Transfer
par: Brien, Darrin O', et autres
Publié: (2025)

Distilling Specialized Orders for Visual Generation
par: Pramanik, Rishav, et autres
Publié: (2025)

Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions
par: González-González, Manuela, et autres
Publié: (2026)

Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition
par: Zeeshan, Muhammad Osama, et autres
Publié: (2025)

PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
par: Neseem, Marina, et autres
Publié: (2024)

Task Switching Without Forgetting via Proximal Decoupling
par: Shamsolmoali, Pourya, et autres
Publié: (2026)

Finetuning CLIP to Reason about Pairwise Differences
par: Sam, Dylan, et autres
Publié: (2024)

Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation
par: Wu, Tsung-Han, et autres
Publié: (2024)

Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher
par: Belal, Atif, et autres
Publié: (2023)

The Easy Path to Robustness: Coreset Selection using Sample Hardness
par: Ramesh, Pranav, et autres
Publié: (2025)

Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
par: Tian, Hongduan, et autres
Publié: (2024)

Vision Transformer Finetuning Benefits from Non-Smooth Components
par: Odonnat, Ambroise, et autres
Publié: (2026)

How (Mis)calibrated is Your Federated CLIP and What To Do About It?
par: Singha, Mainak, et autres
Publié: (2025)

Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
par: Guichemerre, Alexis, et autres
Publié: (2024)