Copertina

Underrepresented in Foundation Model Pretraining Data? A One-Shot Probe

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Vorster, Chris, Maniparambil, Mayug, O'Connor, Noel E., Murphy, Noel, Molloy, Derek
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters
di: Vorster, Chris, et al.
Pubblicazione: (2026)

Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?
di: Hashmi, Anam, et al.
Pubblicazione: (2026)

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks
di: Hoehing, Nils, et al.
Pubblicazione: (2025)

Ensemble Learning with Sparse Hypercolumns
di: Dietlmeier, Julia, et al.
Pubblicazione: (2026)

Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
di: Sirotkin, Kirill, et al.
Pubblicazione: (2024)

Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment
di: Maniparambil, Mayug, et al.
Pubblicazione: (2024)

Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
di: Aleem, Sidra, et al.
Pubblicazione: (2024)

Do Vision and Language Encoders Represent the World Similarly?
di: Maniparambil, Mayug, et al.
Pubblicazione: (2024)

SynSacc: A Blender-to-V2E Pipeline for Synthetic Neuromorphic Eye-Movement Data and Sim-to-Real Spiking Model Training
di: Iddrisu, Khadija, et al.
Pubblicazione: (2026)

Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
di: Rai, Ayush K., et al.
Pubblicazione: (2025)

Parameter-Free Bio-Inspired Channel Attention for Enhanced Cardiac MRI Reconstruction
di: Hashmi, Anam, et al.
Pubblicazione: (2025)

Accelerating Cardiac MRI Reconstruction with CMRatt: An Attention-Driven Approach
di: Hashmi, Anam, et al.
Pubblicazione: (2024)

An accurate detection is not all you need to combat label noise in web-noisy datasets
di: Albert, Paul, et al.
Pubblicazione: (2024)

VLSM-Ensemble: Ensembling CLIP-based Vision-Language Models for Enhanced Medical Image Segmentation
di: Dietlmeier, Julia, et al.
Pubblicazione: (2025)

Cross-Modal Knowledge Distillation for PET-Free Amyloid-Beta Detection from MRI
di: Chiumento, Francesco, et al.
Pubblicazione: (2026)

Towards Label-Free Brain Tumor Segmentation: Unsupervised Learning with Multimodal MRI
di: Comas-Quiles, Gerard, et al.
Pubblicazione: (2025)

Scaling Video Pretraining for Surgical Foundation Models
di: Lu, Sicheng, et al.
Pubblicazione: (2026)

MRGen: Segmentation Data Engine for Underrepresented MRI Modalities
di: Wu, Haoning, et al.
Pubblicazione: (2024)

Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
di: Kaur, Amandeep, et al.
Pubblicazione: (2026)

Visual Instruction Pretraining for Domain-Specific Foundation Models
di: Li, Yuxuan, et al.
Pubblicazione: (2025)

Leveraging Pretrained Diffusion Models for Zero-Shot Part Assembly
di: Zhang, Ruiyuan, et al.
Pubblicazione: (2025)

ProtoSAM: One-Shot Medical Image Segmentation With Foundational Models
di: Ayzenberg, Lev, et al.
Pubblicazione: (2024)

Evaluating Image-Based Face and Eye Tracking with Event Cameras
di: Iddrisu, Khadija, et al.
Pubblicazione: (2024)

Generative Event Pretraining with Foundation Model Alignment
di: Cao, Jianwen, et al.
Pubblicazione: (2026)

Harvest Video Foundation Models via Efficient Post-Pretraining
di: Li, Yizhuo, et al.
Pubblicazione: (2023)

Quadcopter Position Hold Function using Optical Flow in a Smartphone-based Flight Computer
di: Caliston, Noel P., et al.
Pubblicazione: (2025)

DeepATLAS: One-Shot Localization for Biomedical Data
di: Chang, Peter D.
Pubblicazione: (2024)

FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks
di: Miao, Juzheng, et al.
Pubblicazione: (2024)

Scaling Dense Event-Stream Pretraining from Visual Foundation Models
di: Chen, Zhiwen, et al.
Pubblicazione: (2026)

Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing
di: Adler, Mathis Jürgen, et al.
Pubblicazione: (2025)

RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes
di: Baltaxe, Michael, et al.
Pubblicazione: (2026)

Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
di: Zhang, Ziyu, et al.
Pubblicazione: (2025)

MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
di: Wang, Di, et al.
Pubblicazione: (2024)

Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach
di: Rai, Ayush K., et al.
Pubblicazione: (2023)

Lyapunov Probes for Hallucination Detection in Large Foundation Models
di: Luan, Bozhi, et al.
Pubblicazione: (2026)

Probing the 3D Awareness of Visual Foundation Models
di: Banani, Mohamed El, et al.
Pubblicazione: (2024)

Few-Shot Panoptic Segmentation With Foundation Models
di: Käppeler, Markus, et al.
Pubblicazione: (2023)

Data Scaling Laws for Radiology Foundation Models
di: Ilse, Maximilian, et al.
Pubblicazione: (2025)

MotionCrafter: One-Shot Motion Customization of Diffusion Models
di: Zhang, Yuxin, et al.
Pubblicazione: (2023)

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
di: Zhu, Junhan, et al.
Pubblicazione: (2025)