Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.17165 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913245315465216 |
|---|---|
| author | Zaveri, Ram J. Brume, Voke Doretto, Gianfranco |
| author_facet | Zaveri, Ram J. Brume, Voke Doretto, Gianfranco |
| contents | Microscopy data collections are becoming larger and more frequent. Accurate and precise quantitative analysis tools like cell instance segmentation are necessary to benefit from them. This is challenging due to the variability in the data, which requires retraining the segmentation model to maintain high accuracy on new collections. This is needed especially for segmenting cells with elongated and non-convex morphology like bacteria. We propose to reduce the amount of annotation and computing power needed for retraining the model by introducing a few-shot domain adaptation approach that requires annotating only one to five cells of the new data to process and that quickly adapts the model to maintain high accuracy. Our results show a significant boost in accuracy after adaptation to very challenging bacteria datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17165 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Few-shot adaptation for morphology-independent cell instance segmentation Zaveri, Ram J. Brume, Voke Doretto, Gianfranco Computer Vision and Pattern Recognition Microscopy data collections are becoming larger and more frequent. Accurate and precise quantitative analysis tools like cell instance segmentation are necessary to benefit from them. This is challenging due to the variability in the data, which requires retraining the segmentation model to maintain high accuracy on new collections. This is needed especially for segmenting cells with elongated and non-convex morphology like bacteria. We propose to reduce the amount of annotation and computing power needed for retraining the model by introducing a few-shot domain adaptation approach that requires annotating only one to five cells of the new data to process and that quickly adapts the model to maintain high accuracy. Our results show a significant boost in accuracy after adaptation to very challenging bacteria datasets. |
| title | Few-shot adaptation for morphology-independent cell instance segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.17165 |