A Note on Knowledge Distillation Loss Function for Object Classification
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916370196725760 |
|---|---|
| author | Chen, Defang |
| author_facet | Chen, Defang |
| contents | This research note provides a quick introduction to the knowledge distillation loss function used in object classification. In particular, we discuss its connection to a previously proposed logits matching loss function. We further treat knowledge distillation as a specific form of output regularization and demonstrate its connection to label smoothing and entropy-based regularization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2109_06458 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | A Note on Knowledge Distillation Loss Function for Object Classification Chen, Defang Machine Learning Artificial Intelligence This research note provides a quick introduction to the knowledge distillation loss function used in object classification. In particular, we discuss its connection to a previously proposed logits matching loss function. We further treat knowledge distillation as a specific form of output regularization and demonstrate its connection to label smoothing and entropy-based regularization. |
| title | A Note on Knowledge Distillation Loss Function for Object Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2109.06458 |