How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913451980357632 |
|---|---|
| author | Holste, Gregory Jiang, Ziyu Jaiswal, Ajay Hanna, Maria Minkowitz, Shlomo Legasto, Alan C. Escalon, Joanna G. Steinberger, Sharon Bittman, Mark Shen, Thomas C. Ding, Ying Summers, Ronald M. Shih, George Peng, Yifan Wang, Zhangyang |
| author_facet | Holste, Gregory Jiang, Ziyu Jaiswal, Ajay Hanna, Maria Minkowitz, Shlomo Legasto, Alan C. Escalon, Joanna G. Steinberger, Sharon Bittman, Mark Shen, Thomas C. Ding, Ying Summers, Ronald M. Shih, George Peng, Yifan Wang, Zhangyang |
| contents | Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. However, the nuanced ways in which pruning impacts model behavior are not well understood, particularly for long-tailed, multi-label datasets commonly found in clinical settings. This knowledge gap could have dangerous implications when deploying a pruned model for diagnosis, where unexpected model behavior could impact patient well-being. To fill this gap, we perform the first analysis of pruning's effect on neural networks trained to diagnose thorax diseases from chest X-rays (CXRs). On two large CXR datasets, we examine which diseases are most affected by pruning and characterize class "forgettability" based on disease frequency and co-occurrence behavior. Further, we identify individual CXRs where uncompressed and heavily pruned models disagree, known as pruning-identified exemplars (PIEs), and conduct a human reader study to evaluate their unifying qualities. We find that radiologists perceive PIEs as having more label noise, lower image quality, and higher diagnosis difficulty. This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification. All code, model weights, and data access instructions can be found at https://github.com/VITA-Group/PruneCXR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_09180 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers? Holste, Gregory Jiang, Ziyu Jaiswal, Ajay Hanna, Maria Minkowitz, Shlomo Legasto, Alan C. Escalon, Joanna G. Steinberger, Sharon Bittman, Mark Shen, Thomas C. Ding, Ying Summers, Ronald M. Shih, George Peng, Yifan Wang, Zhangyang Computer Vision and Pattern Recognition Artificial Intelligence Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. However, the nuanced ways in which pruning impacts model behavior are not well understood, particularly for long-tailed, multi-label datasets commonly found in clinical settings. This knowledge gap could have dangerous implications when deploying a pruned model for diagnosis, where unexpected model behavior could impact patient well-being. To fill this gap, we perform the first analysis of pruning's effect on neural networks trained to diagnose thorax diseases from chest X-rays (CXRs). On two large CXR datasets, we examine which diseases are most affected by pruning and characterize class "forgettability" based on disease frequency and co-occurrence behavior. Further, we identify individual CXRs where uncompressed and heavily pruned models disagree, known as pruning-identified exemplars (PIEs), and conduct a human reader study to evaluate their unifying qualities. We find that radiologists perceive PIEs as having more label noise, lower image quality, and higher diagnosis difficulty. This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification. All code, model weights, and data access instructions can be found at https://github.com/VITA-Group/PruneCXR. |
| title | How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers? |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2308.09180 |