Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization

arXiv:2604.10970v1 Announce Type: new Abstract: Background: Task-specific microscopy datasets are often small, making it difficult to train deep learning models that learn robust features. While self-supervised learning (SSL) has shown promise through pretraining on large, domain-specific datasets, generalizability across datasets with differing staining protocols and channel configurations remains underexplored. We investigated the generalizability of SSL models pretrained on ImageNet-1k and HPA FOV, evaluating their embeddings on OpenCell with and without fine-tuning, two channel-mismatch strategies, and varying fine-tuning data fractions. We additionally analyzed single-cell embeddings on a labeled OpenCell subset. Result: DINO-based ViT backbones pretrained on HPA FOV or ImageNet-1k transfer well to OpenCell even without fine-tuning. The HPA FOV-pretrained model achieved the highest zero-shot performance (macro F_1 0.822 pm 0.007). Fine-tuning further improved performance to 0.860 pm 0.013. At the single-cell level, the HPA single-cell-pretrained model achieved the highest k-nearest neighbor performance across all neighborhood sizes (macro F_1 geq 0.796). Conclusion: SSL methods like DINO, pretrained on large domain-relevant datasets, enable effective use of deep learning features for fine-tuning on small, task-specific microscopy datasets.

Related

• M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model
• Needle in a Haystack -- One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytology
• PASTA: Vision Transformer Patch Aggregation for Weakly Supervised Target and Anomaly Segmentation
• Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR

Source: arXiv cs.CV | 2026-04-14