Imagen de Portada

Why Fine-grained Labels in Pretraining Benefit Generalization?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hong, Guan Zhe, Cui, Yin, Fuxman, Ariel, Chan, Stanley, Luo, Enming
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning 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

Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use
por: Toubal, Imad Eddine, et al.
Publicado: (2024)

ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation
por: Dong, Chengyu, et al.
Publicado: (2025)

Agile Deliberation: Concept Deliberation for Subjective Visual Classification
por: Wang, Leijie, et al.
Publicado: (2025)

Negative Label Guided OOD Detection with Pretrained Vision-Language Models
por: Jiang, Xue, et al.
Publicado: (2024)

Tutorial on Diffusion Models for Imaging and Vision
por: Chan, Stanley H.
Publicado: (2024)

Automatic Fine-grained Segmentation-assisted Report Generation
por: Jonske, Frederic, et al.
Publicado: (2025)

Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement
por: Bala, Gouranga, et al.
Publicado: (2024)

Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning
por: Elmimouni, Zakarya, et al.
Publicado: (2026)

Fine-grained Classes and How to Find Them
por: Grcić, Matej, et al.
Publicado: (2024)

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
por: Hu, Yushi, et al.
Publicado: (2023)

Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
por: BOURCIER, Jules, et al.
Publicado: (2022)

Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
por: Luo, Yaxin, et al.
Publicado: (2026)

Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
por: Hu, Jiamian, et al.
Publicado: (2024)

FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval
por: Gardères, François, et al.
Publicado: (2026)

FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
por: Dave, Ishan Rajendrakumar, et al.
Publicado: (2024)

Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding
por: Xu, Lilin, et al.
Publicado: (2025)

Is Large-Scale Pretraining the Secret to Good Domain Generalization?
por: Teterwak, Piotr, et al.
Publicado: (2024)

Understanding Flatness in Generative Models: Its Role and Benefits
por: Lee, Taehwan, et al.
Publicado: (2025)

CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing
por: Bossemeyer, Leonie, et al.
Publicado: (2025)

Phoenix: A Federated Generative Diffusion Model
por: Jothiraj, Fiona Victoria Stanley, et al.
Publicado: (2023)

InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
por: Huang, Zhe, et al.
Publicado: (2024)

SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models
por: Yi, Huahui, et al.
Publicado: (2025)

SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization
por: Huang, Yongle, et al.
Publicado: (2025)

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models
por: Qu, Helen, et al.
Publicado: (2025)

Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding
por: Mao, Ye, et al.
Publicado: (2026)

FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
por: Xie, Chunyu, et al.
Publicado: (2025)

Why Does It Look There? Structured Explanations for Image Classification
por: Li, Jiarui, et al.
Publicado: (2026)

Urban Representation Learning for Fine-grained Economic Mapping: A Semi-supervised Graph-based Approach
por: Cao, Jinzhou, et al.
Publicado: (2025)

Pretrained Visual Uncertainties
por: Kirchhof, Michael, et al.
Publicado: (2024)

Towards Understanding Why Data Augmentation Improves Generalization
por: Li, Jingyang, et al.
Publicado: (2025)

Fine-grained Hierarchical Crop Type Classification from Integrated Hyperspectral EnMAP Data and Multispectral Sentinel-2 Time Series: A Large-scale Dataset and Dual-stream Transformer Method
por: Li, Wenyuan, et al.
Publicado: (2025)

Fine-tuned Vision Language Model for Localization of Parasitic Eggs in Microscopic Images
por: Sien, Chan Hao, et al.
Publicado: (2026)

Siamese Networks with Soft Labels for Unsupervised Lesion Detection and Patch Pretraining on Screening Mammograms
por: Van Vorst, Kevin, et al.
Publicado: (2024)

A Transformer-based Multimodal Fusion Model for Efficient Crowd Counting Using Visual and Wireless Signals
por: Cui, Zhe, et al.
Publicado: (2025)

Accelerating Augmentation Invariance Pretraining
por: Lin, Jinhong, et al.
Publicado: (2024)

FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
por: Jian, Xiangru, et al.
Publicado: (2026)

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

When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
por: Luo, You-Wei, et al.
Publicado: (2024)

Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
por: Gu, Hanlin, et al.
Publicado: (2024)

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
por: Zhou, Mingyuan, et al.
Publicado: (2024)