Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.11161 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917850619314176 |
|---|---|
| author | Wang, Jun Mao, Yu Cui, Yufei Guan, Nan Xue, Chun Jason |
| author_facet | Wang, Jun Mao, Yu Cui, Yufei Guan, Nan Xue, Chun Jason |
| contents | Pre-processing whole slide images (WSIs) can impact classification performance. Our study shows that using fixed hyper-parameters for pre-processing out-of-domain WSIs can significantly degrade performance. Therefore, it is critical to search domain-specific hyper-parameters during inference. However, searching for an optimal parameter set is time-consuming. To overcome this, we propose BAHOP, a novel Similarity-based Basin Hopping optimization for fast parameter tuning to enhance inference performance on out-of-domain data. The proposed BAHOP achieves 5\% to 30\% improvement in accuracy with $\times5$ times faster on average. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11161 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BAHOP: Similarity-based Basin Hopping for A fast hyper-parameter search in WSI classification Wang, Jun Mao, Yu Cui, Yufei Guan, Nan Xue, Chun Jason Computer Vision and Pattern Recognition Machine Learning Pre-processing whole slide images (WSIs) can impact classification performance. Our study shows that using fixed hyper-parameters for pre-processing out-of-domain WSIs can significantly degrade performance. Therefore, it is critical to search domain-specific hyper-parameters during inference. However, searching for an optimal parameter set is time-consuming. To overcome this, we propose BAHOP, a novel Similarity-based Basin Hopping optimization for fast parameter tuning to enhance inference performance on out-of-domain data. The proposed BAHOP achieves 5\% to 30\% improvement in accuracy with $\times5$ times faster on average. |
| title | BAHOP: Similarity-based Basin Hopping for A fast hyper-parameter search in WSI classification |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.11161 |