Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,19 @@ metrics:
|
|
| 7 |
pipeline_tag: feature-extraction
|
| 8 |
tags:
|
| 9 |
- art
|
| 10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pipeline_tag: feature-extraction
|
| 8 |
tags:
|
| 9 |
- art
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
| Model | F1 Score | Precision | Recall | Threshold | Cluster 2 | Cluster Free |
|
| 13 |
+
|:-----------------------------------:|:----------:|:-----------:|:--------:|:-----------:|:-----------:|:--------------:|
|
| 14 |
+
| ccip-caformer-2-randaug-pruned_fp32 | 0.78561 | 0.800148 | 0.771592 | 0.171053 | 0.686617 | 0.728195 |
|
| 15 |
+
| ccip-caformer-23_randaug_fp32 | 0.81625 | 0.854134 | 0.781585 | 0.136797 | 0.745697 | 0.8068 |
|
| 16 |
+
| ccip-caformer-24-randaug-pruned | 0.917211 | 0.933481 | 0.901499 | 0.178475 | 0.890366 | 0.922375 |
|
| 17 |
+
| ccip-caformer-2_fp32 | 0.755125 | 0.790172 | 0.723055 | 0.141275 | 0.64977 | 0.718516 |
|
| 18 |
+
| ccip-caformer-4_fp32 | 0.844967 | 0.870553 | 0.820842 | 0.18367 | 0.795565 | 0.868133 |
|
| 19 |
+
| ccip-caformer-5_fp32 | 0.864363 | 0.90155 | 0.830121 | 0.183973 | 0.792051 | 0.862289 |
|
| 20 |
+
| ccip-caformer-6-randaug-pruned_fp32 | 0.878403 | 0.893648 | 0.863669 | 0.195122 | 0.810176 | 0.897904 |
|
| 21 |
+
| ccip-caformer_query-12 | 0.823928 | 0.871122 | 0.781585 | 0.141308 | 0.787237 | 0.809426 |
|
| 22 |
+
|
| 23 |
+
* The calculation of `F1 Score`, `Precision`, and `Recall` considers "the characters in both images are the same" as a positive case. `Threshold` is determined by finding the maximum value on the F1 Score curve.
|
| 24 |
+
* `Cluster_2` represents the approximate optimal clustering solution obtained by tuning the eps value in DBSCAN clustering algorithm with min_samples set to `2`, and evaluating the similarity between the obtained clusters and the true distribution using the `random_adjust_score`.
|
| 25 |
+
* `Cluster_Free` represents the approximate optimal solution obtained by tuning the `max_eps` and `min_samples` values in the OPTICS clustering algorithm, and evaluating the similarity between the obtained clusters and the true distribution using the `random_adjust_score`.
|