Out-of-distribution evaluations of channel agnostic masked autoencoders in fluorescence microscopy
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908283480047616 |
|---|---|
| author | Hurry, Christian John Zhang, Jinjie Ishola, Olubukola Slade, Emma Nguyen, Cuong Q. |
| author_facet | Hurry, Christian John Zhang, Jinjie Ishola, Olubukola Slade, Emma Nguyen, Cuong Q. |
| contents | Developing computer vision for high-content screening is challenging due to various sources of distribution-shift caused by changes in experimental conditions, perturbagens, and fluorescent markers. The impact of different sources of distribution-shift are confounded in typical evaluations of models based on transfer learning, which limits interpretations of how changes to model design and training affect generalisation. We propose an evaluation scheme that isolates sources of distribution-shift using the JUMP-CP dataset, allowing researchers to evaluate generalisation with respect to specific sources of distribution-shift. We then present a channel-agnostic masked autoencoder $\mathbf{Campfire}$ which, via a shared decoder for all channels, scales effectively to datasets containing many different fluorescent markers, and show that it generalises to out-of-distribution experimental batches, perturbagens, and fluorescent markers, and also demonstrates successful transfer learning from one cell type to another. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Out-of-distribution evaluations of channel agnostic masked autoencoders in fluorescence microscopy Hurry, Christian John Zhang, Jinjie Ishola, Olubukola Slade, Emma Nguyen, Cuong Q. Machine Learning Computer Vision and Pattern Recognition Developing computer vision for high-content screening is challenging due to various sources of distribution-shift caused by changes in experimental conditions, perturbagens, and fluorescent markers. The impact of different sources of distribution-shift are confounded in typical evaluations of models based on transfer learning, which limits interpretations of how changes to model design and training affect generalisation. We propose an evaluation scheme that isolates sources of distribution-shift using the JUMP-CP dataset, allowing researchers to evaluate generalisation with respect to specific sources of distribution-shift. We then present a channel-agnostic masked autoencoder $\mathbf{Campfire}$ which, via a shared decoder for all channels, scales effectively to datasets containing many different fluorescent markers, and show that it generalises to out-of-distribution experimental batches, perturbagens, and fluorescent markers, and also demonstrates successful transfer learning from one cell type to another. |
| title | Out-of-distribution evaluations of channel agnostic masked autoencoders in fluorescence microscopy |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.19149 |