Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# Pinpoint Counterfactuals: localized gender counterfactual generation (NeurIPS 2025 Datasets and Benchmarks track. Submission 1386)
|
| 6 |
+
|
| 7 |
+
## Getting started
|
| 8 |
+
|
| 9 |
+
To generate PinPoint Counterfactuals, take the following steps.
|
| 10 |
+
|
| 11 |
+
### Download the data
|
| 12 |
+
|
| 13 |
+
First, download the <a href="https://ai.meta.com/datasets/facet-downloads/">FACET</a> and <a href="https://ai.google.com/research/ConceptualCaptions/download">CC3M</a> dataset. Unpack them in the directory of your choice.
|
| 14 |
+
|
| 15 |
+
### Generating PP masks
|
| 16 |
+
|
| 17 |
+
Use the `Color-Invariant-Skin-Segmentation` module to generate masks, following the methodology outlined in the main submission manuscript.
|
| 18 |
+
|
| 19 |
+
### In-paint the images
|
| 20 |
+
|
| 21 |
+
Use the `BrushNet` module to in-paint the images from FACET and/or CC3M (see the respective scripts in `BrushNet/examples/brushnet/inapaint_*.py`.
|