Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,8 @@ co2_eq_emissions:
|
|
| 29 |
|
| 30 |
This model is a multimodal classifier that combines text and image inputs to detect potential bias in content. It uses a BERT-based text encoder and a ResNet-34 image encoder, which are fused for classification purposes. A contrastive learning approach was used during training, leveraging CLIP embeddings as guidance to align the text and image representations.
|
| 31 |
|
|
|
|
|
|
|
| 32 |
## Model Details
|
| 33 |
|
| 34 |
- **Text Encoder**: BERT (`bert-base-uncased`)
|
|
@@ -152,6 +154,7 @@ def load_model():
|
|
| 152 |
return model
|
| 153 |
```
|
| 154 |
|
|
|
|
| 155 |
|
| 156 |
```python
|
| 157 |
import torch
|
|
|
|
| 29 |
|
| 30 |
This model is a multimodal classifier that combines text and image inputs to detect potential bias in content. It uses a BERT-based text encoder and a ResNet-34 image encoder, which are fused for classification purposes. A contrastive learning approach was used during training, leveraging CLIP embeddings as guidance to align the text and image representations.
|
| 31 |
|
| 32 |
+
This model is based on [FND-CLIP](https://arxiv.org/pdf/2205.14304), proposed by Zhou et al. 2022.
|
| 33 |
+
|
| 34 |
## Model Details
|
| 35 |
|
| 36 |
- **Text Encoder**: BERT (`bert-base-uncased`)
|
|
|
|
| 154 |
return model
|
| 155 |
```
|
| 156 |
|
| 157 |
+
## How to Run the Model
|
| 158 |
|
| 159 |
```python
|
| 160 |
import torch
|