Copertina

Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Khan, Behraj, Syed, Tahir
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models
di: Khan, Behraj, et al.
Pubblicazione: (2025)

Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
di: Khan, Behraj, et al.
Pubblicazione: (2025)

Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images
di: Usman, Annayah, et al.
Pubblicazione: (2026)

Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations
di: Azeem, Hiba, et al.
Pubblicazione: (2026)

Mitigating covariate shift in non-colocated data with learned parameter priors
di: Khan, Behraj, et al.
Pubblicazione: (2024)

Retrieval-enriched zero-shot image classification in low-resource domains
di: Dall'Asen, Nicola, et al.
Pubblicazione: (2024)

Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift
di: Khan, Behraj, et al.
Pubblicazione: (2025)

Latents of latents to delineate pixels: hybrid Matryoshka autoencoder-to-U-Net pairing for segmenting large medical images in GPU-poor and low-data regimes
di: Syed, Tahir, et al.
Pubblicazione: (2025)

Multi-label classification for multi-temporal, multi-spatial coral reef condition monitoring using vision foundation model with adapter learning
di: Shao, Xinlei, et al.
Pubblicazione: (2025)

Attention to details, logits to truth: visual-aware attention and logits enhancement to mitigate hallucinations in LVLMs
di: Wang, Jingyi, et al.
Pubblicazione: (2026)

Accurate and efficient zero-shot 6D pose estimation with frozen foundation models
di: Caraffa, Andrea, et al.
Pubblicazione: (2025)

Zero-shot segmentation of skin tumors in whole-slide images with vision-language foundation models
di: Moreno, Santiago, et al.
Pubblicazione: (2025)

Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
di: Elbarz, Walid, et al.
Pubblicazione: (2025)

Label-efficient underwater species classification with logistic regression on frozen foundation model embeddings
di: Rost, Thomas Manuel
Pubblicazione: (2026)

Colony Grounded SAM2: Zero-shot detection and segmentation of bacterial colonies using foundation models
di: Korporaal, Daan, et al.
Pubblicazione: (2026)

Are vision-language models ready to zero-shot replace supervised classification models in agriculture?
di: Ranario, Earl, et al.
Pubblicazione: (2025)

Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms
di: Sanghvi, Samyak, et al.
Pubblicazione: (2026)

Streamline pathology foundation model by cross-magnification distillation
di: Su, Ziyu, et al.
Pubblicazione: (2025)

Multiple data sources and domain generalization learning method for road surface defect classification
di: Trinh, Linh, et al.
Pubblicazione: (2024)

FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models
di: Caraffa, Andrea, et al.
Pubblicazione: (2023)

CXR-CML: Improved zero-shot classification of long-tailed multi-label diseases in Chest X-Rays
di: Madhipati, Rajesh, et al.
Pubblicazione: (2025)

Multimodal HIE Lesion Segmentation in Neonates: A Comparative Study of Loss Functions
di: Usman, Annayah, et al.
Pubblicazione: (2025)

ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
di: Turbé, Hugues, et al.
Pubblicazione: (2024)

Diverse and Tailored Image Generation for Zero-shot Multi-label Classification
di: Zhang, Kaixin, et al.
Pubblicazione: (2024)

Initialization matters in few-shot adaptation of vision-language models for histopathological image classification
di: Meseguer, Pablo, et al.
Pubblicazione: (2026)

Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement
di: Huang, Weijian, et al.
Pubblicazione: (2024)

CoDi -- an exemplar-conditioned diffusion model for low-shot counting
di: Šuštar, Grega, et al.
Pubblicazione: (2025)

Autonomous labeling of surgical resection margins using a foundation model
di: Yang, Xilin, et al.
Pubblicazione: (2025)

Do computer vision foundation models learn the low-level characteristics of the human visual system?
di: Cai, Yancheng, et al.
Pubblicazione: (2025)

LPN: Language-guided Prototypical Network for few-shot classification
di: Cheng, Kaihui, et al.
Pubblicazione: (2023)

Adaptive Prototype Model for Attribute-based Multi-label Few-shot Action Recognition
di: Xiao, Juefeng, et al.
Pubblicazione: (2025)

Improving Pseudo-labelling and Enhancing Robustness for Semi-Supervised Domain Generalization
di: Khan, Adnan, et al.
Pubblicazione: (2024)

Adaptive Semantic Consistency for Cross-domain Few-shot Classification
di: Lu, Hengchu, et al.
Pubblicazione: (2023)

Ecological mapping with geospatial foundation models
di: Mahlasi, Craig, et al.
Pubblicazione: (2026)

Towards a general-purpose foundation model for fMRI analysis
di: Wang, Cheng, et al.
Pubblicazione: (2025)

CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray
di: Lin, Mingquan, et al.
Pubblicazione: (2025)

DA-SSL: self-supervised domain adaptor to leverage foundational models in turbt histopathology slides
di: Zhang, Haoyue, et al.
Pubblicazione: (2025)

Geospatial foundation models for image analysis: evaluating and enhancing NASA-IBM Prithvi's domain adaptability
di: Hsu, Chia-Yu, et al.
Pubblicazione: (2024)

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2025)

PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection
di: Gao, Yingjie, et al.
Pubblicazione: (2024)