Add YAML metadata frontmatter
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 1-Parameter Classifier
|
| 2 |
|
| 3 |
Progressively reducing the model budget for image-level person classification on EUPE-ViT-B features. Each stage is a deeper reduction or transformation of the previous. The classifier shrinks across stages while the backbone it draws features from is attacked in parallel.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: fair-research-license
|
| 4 |
+
license_link: https://huggingface.co/facebook/EUPE-ViT-B/blob/main/LICENSE
|
| 5 |
+
base_model: facebook/EUPE-ViT-B
|
| 6 |
+
tags:
|
| 7 |
+
- image-classification
|
| 8 |
+
- binary-classification
|
| 9 |
+
- minimal-models
|
| 10 |
+
- interpretability
|
| 11 |
+
- vision-transformer
|
| 12 |
+
- feature-engram
|
| 13 |
+
library_name: pytorch
|
| 14 |
+
datasets:
|
| 15 |
+
- detection-datasets/coco
|
| 16 |
+
pipeline_tag: image-classification
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
# 1-Parameter Classifier
|
| 20 |
|
| 21 |
Progressively reducing the model budget for image-level person classification on EUPE-ViT-B features. Each stage is a deeper reduction or transformation of the previous. The classifier shrinks across stages while the backbone it draws features from is attacked in parallel.
|