# Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization Source: [Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization]() Collection index: [llms.txt]() Data updated: 2026-04-15T05:00:18.272Z Authors: Ben Isselmann, Dilara G\\"oksu, Heinz Neumann, Andreas Weinmann Published: 2026-04-13T04:14:01.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()