Update README.md
Browse files
README.md
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-nc-4.0
|
| 3 |
-
datasets:
|
| 4 |
-
- DBD-research-group/BirdSet
|
| 5 |
-
base_model:
|
| 6 |
-
- facebook/convnext-base-224-22k
|
| 7 |
-
pipeline_tag: audio-classification
|
| 8 |
-
library_name: transformers
|
| 9 |
-
tags:
|
| 10 |
-
- audio-classification
|
| 11 |
-
- audio
|
| 12 |
-
---
|
| 13 |
# AudioProtoPNet: An Interpretable Deep Learning Model for Bird Sound Classification
|
| 14 |
|
| 15 |
-
## Model Description
|
| 16 |
|
| 17 |
-
|
|
|
|
| 18 |
|
| 19 |
Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species
|
| 20 |
based on their vocalizations. However, traditional deep learning models are often "black boxes," providing
|
|
@@ -32,6 +32,10 @@ During inference, recordings are classified by comparing them to learned prototy
|
|
| 32 |
providing explanations for the model's decisions and insights into the most informative embeddings of each
|
| 33 |
bird species.
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
### Training Data
|
| 36 |
|
| 37 |
The model was trained on the **BirdSet training dataset**, which comprises 9734 bird species and over 6800
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- DBD-research-group/BirdSet
|
| 5 |
+
base_model:
|
| 6 |
+
- facebook/convnext-base-224-22k
|
| 7 |
+
pipeline_tag: audio-classification
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- audio-classification
|
| 11 |
+
- audio
|
| 12 |
+
---
|
| 13 |
# AudioProtoPNet: An Interpretable Deep Learning Model for Bird Sound Classification
|
| 14 |
|
|
|
|
| 15 |
|
| 16 |
+
|
| 17 |
+
## Abstract
|
| 18 |
|
| 19 |
Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species
|
| 20 |
based on their vocalizations. However, traditional deep learning models are often "black boxes," providing
|
|
|
|
| 32 |
providing explanations for the model's decisions and insights into the most informative embeddings of each
|
| 33 |
bird species.
|
| 34 |
|
| 35 |
+
- **Paper**: [Elsevier](www.sciencedirect.com/science/article/pii/S1574954125000901)
|
| 36 |
+
|
| 37 |
+
## Model Description
|
| 38 |
+
|
| 39 |
### Training Data
|
| 40 |
|
| 41 |
The model was trained on the **BirdSet training dataset**, which comprises 9734 bird species and over 6800
|