Imagen de Portada

Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Zitong, Wang, Haoyu
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation
por: Wang, Haoyu, et al.
Publicado: (2026)

Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models
por: Fan, Jiawei, et al.
Publicado: (2026)

Frozen Vision Transformers for Dense Prediction on Small Datasets: A Case Study in Arrow Localization
por: Shepherd, Maxwell
Publicado: (2026)

FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
por: Chen, Xi, et al.
Publicado: (2024)

Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation
por: Banerjee, Sweta, et al.
Publicado: (2025)

Beyond the Failures: Rethinking Foundation Models in Pathology
por: Tizhoosh, Hamid R.
Publicado: (2025)

Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
por: Fu, Shenghao, et al.
Publicado: (2024)

Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
por: Zhang, Tianxiao, et al.
Publicado: (2024)

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
por: Chen, Dong, et al.
Publicado: (2026)

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
por: Wang, Jiayi, et al.
Publicado: (2025)

Vision Large Language Models Are Good Noise Handlers in Engagement Analysis
por: Vedernikov, Alexander, et al.
Publicado: (2025)

MedFM-Robust: Benchmarking Robustness of Medical Foundation Models
por: Cui, Xiangxiang, et al.
Publicado: (2026)

Asymmetric Masked Distillation for Pre-Training Small Foundation Models
por: Zhao, Zhiyu, et al.
Publicado: (2023)

Rethinking Generalizable Infrared Small Target Detection: A Real-scene Benchmark and Cross-view Representation Learning
por: Lu, Yahao, et al.
Publicado: (2025)

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
por: Tang, Song, et al.
Publicado: (2023)

Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach
por: Pan, Qihe, et al.
Publicado: (2024)

GuiDINO: Rethinking Vision Foundation Model in Medical Image Segmentation
por: Liang, Zhuonan, et al.
Publicado: (2026)

Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm
por: Yu, Chuang, et al.
Publicado: (2025)

In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model
por: Yin, Junhui, et al.
Publicado: (2024)

REOBench: Benchmarking Robustness of Earth Observation Foundation Models
por: Li, Xiang, et al.
Publicado: (2025)

Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise
por: Gao, Yansheng, et al.
Publicado: (2025)

SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
por: Dünkel, Olaf, et al.
Publicado: (2026)

Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond
por: Zhang, Fan, et al.
Publicado: (2025)

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training
por: Wang, Yanyun, et al.
Publicado: (2025)

Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
por: Farronato, Nicola, et al.
Publicado: (2026)

Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding
por: Truong, Thanh-Dat, et al.
Publicado: (2025)

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
por: Ma, Yingzi, et al.
Publicado: (2024)

Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection
por: Li, Yuehui, et al.
Publicado: (2025)

Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models
por: Saddik, Izaldein Al-Zyoud Abdulmotaleb El
Publicado: (2026)

Towards Training-free Anomaly Detection with Vision and Language Foundation Models
por: Zhang, Jinjin, et al.
Publicado: (2025)

Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
por: Vemulapalli, Raviteja, et al.
Publicado: (2023)

Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models
por: Orlova, Svetlana, et al.
Publicado: (2026)

Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images
por: Zou, Xuechao, et al.
Publicado: (2024)

Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving
por: Keser, Mert, et al.
Publicado: (2025)

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
por: Li, Xianhang, et al.
Publicado: (2025)

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

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
por: Wang, Xintong, et al.
Publicado: (2025)

All-in-One: Transferring Vision Foundation Models into Stereo Matching
por: Zhou, Jingyi, et al.
Publicado: (2024)

DDFAV: Remote Sensing Large Vision Language Models Dataset and Evaluation Benchmark
por: Li, Haodong, et al.
Publicado: (2024)

Training A Small Emotional Vision Language Model for Visual Art Comprehension
por: Zhang, Jing, et al.
Publicado: (2024)