Can You Trust Frozen Hematology Foundation Models under Acquisition Shift?

arXiv:2608.25148 · cs.CV, cs.AI, q-bio.QM · Submitted 2026-08-25 · Read on arXiv

cs.CV, cs.AI, q-bio.QM

Submitted: 2026-08-25

Updated: 2026-08-25

Project page: https://jaishrm07.github.io/hematology-fm-robustness

Terminology

• Accuracy — 38× in this paper · explained in 1 episode
• Calibration — 33× in this paper · explained in 7 episodes
• Robustness — 30× in this paper · explained in 5 episodes
• Adaptation — 28× in this paper · explained in 1 episode
• Foundation Model — 24× in this paper · explained in 3 episodes
• Benchmark — 21× in this paper · explained in 2 episodes
• Foundation Models — 21× in this paper · explained in 7 episodes
• Regret — 15× in this paper · explained in 3 episodes
• Embeddings — 9× in this paper · explained in 2 episodes
• Linear probe — 7× in this paper · explained in 2 episodes
• Domain Shift — 4× in this paper · explained in 4 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 4 episodes
• Distribution Shift — 3× in this paper · explained in 6 episodes
• Domain Adaptation — 3× in this paper · explained in 5 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Class-Balanced Re-standardization — 2× in this paper
• Expected Calibration Error — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• Core — 1× in this paper · explained in 2 episodes
• Covariate Shift — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 4 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Models (FMs) — 1× in this paper · explained in 2 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology
• RedDino: A foundation model for red blood cell analysis
• Benchmarking White Blood Cell Classification Under Domain Shift
• Measuring Robustness to Natural Distribution Shifts in Image Classification
• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
• Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss
• WBCBench 2026: A Challenge for Robust White Blood Cell Classification Under Class Imbalance
• Revisiting Batch Normalization For Practical Domain Adaptation
• Improving robustness against common corruptions by covariate shift adaptation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Tent: Fully Test-time Adaptation by Entropy Minimization
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation
• DINOv2: Learning Robust Visual Features without Supervision
• EVA-02: A Visual Representation for Neon Genesis
• Benchmarking Self-Supervised Learning on Diverse Pathology Datasets
• BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
• Learning Transferable Visual Models From Natural Language Supervision
• Deep Residual Learning for Image Recognition
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models