Emojis
Browse files
app.py
CHANGED
|
@@ -69,31 +69,31 @@ with demo:
|
|
| 69 |
# Centered Title and Welcome message
|
| 70 |
gr.HTML("""
|
| 71 |
<div style="text-align:center;">
|
| 72 |
-
<h1>Deepfake Detection Arena (DFD) Leaderboard</h1>
|
| 73 |
</div>
|
| 74 |
""")
|
| 75 |
|
| 76 |
# Description/Intro Section
|
| 77 |
gr.Markdown("""
|
| 78 |
-
# The Open Benchmark for Detecting AI-Generated Images
|
| 79 |
|
| 80 |
[DFD-Arena](https://github.com/BitMind-AI/dfd-arena) is the first benchmark to address the open-source computer vision community's need for a **comprehensive evaluation framework for state-of-the-art (SOTA) detection of AI-generated images**.
|
| 81 |
|
| 82 |
While [previous studies](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9721302) have focused on benchmarking the SOTA on content-specific subsets of the deepfake detection problem, e.g. human face deepfake benchmarking via [DeepfakeBench](https://github.com/SCLBD/DeepfakeBench), these benchmarks do not adequately account for the broad spectrum of real and generated image types seen in everyday scenarios.
|
| 83 |
|
| 84 |
-
### Explore DFD-Arena
|
| 85 |
|
| 86 |
Learn how the framework evaluates on diverse, content-rich images with semantic balance between real and generated data
|
| 87 |
|
| 88 |
-
- [DFD Arena GitHub repository](https://github.com/BitMind-AI/dfd-arena)
|
| 89 |
|
| 90 |
-
- [Companion blog page](https://bitmindlabs.notion.site/BitMind-Deepfake-Detection-Arena-106af85402838007830ece5a6f3f35a8?pvs=25)
|
| 91 |
|
| 92 |
-
### Authorship
|
| 93 |
|
| 94 |
Both DFD-Arena and novel synthetic image datasets used for evaluation are created by [BitMind](https://www.bitmind.ca/).
|
| 95 |
|
| 96 |
-
- [X/Twitter: @BitMindAI](https://x.com/BitMindAI)
|
| 97 |
""")
|
| 98 |
|
| 99 |
with gr.Tabs():
|
|
|
|
| 69 |
# Centered Title and Welcome message
|
| 70 |
gr.HTML("""
|
| 71 |
<div style="text-align:center;">
|
| 72 |
+
<h1> Deepfake Detection Arena (DFD) Leaderboard</h1>
|
| 73 |
</div>
|
| 74 |
""")
|
| 75 |
|
| 76 |
# Description/Intro Section
|
| 77 |
gr.Markdown("""
|
| 78 |
+
# 🎯 The Open Benchmark for Detecting AI-Generated Images
|
| 79 |
|
| 80 |
[DFD-Arena](https://github.com/BitMind-AI/dfd-arena) is the first benchmark to address the open-source computer vision community's need for a **comprehensive evaluation framework for state-of-the-art (SOTA) detection of AI-generated images**.
|
| 81 |
|
| 82 |
While [previous studies](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9721302) have focused on benchmarking the SOTA on content-specific subsets of the deepfake detection problem, e.g. human face deepfake benchmarking via [DeepfakeBench](https://github.com/SCLBD/DeepfakeBench), these benchmarks do not adequately account for the broad spectrum of real and generated image types seen in everyday scenarios.
|
| 83 |
|
| 84 |
+
### 🔍 Explore DFD-Arena
|
| 85 |
|
| 86 |
Learn how the framework evaluates on diverse, content-rich images with semantic balance between real and generated data
|
| 87 |
|
| 88 |
+
- 📂 [DFD Arena GitHub repository](https://github.com/BitMind-AI/dfd-arena)
|
| 89 |
|
| 90 |
+
- 📝 [Companion blog page](https://bitmindlabs.notion.site/BitMind-Deepfake-Detection-Arena-106af85402838007830ece5a6f3f35a8?pvs=25)
|
| 91 |
|
| 92 |
+
### ✍️ Authorship
|
| 93 |
|
| 94 |
Both DFD-Arena and novel synthetic image datasets used for evaluation are created by [BitMind](https://www.bitmind.ca/).
|
| 95 |
|
| 96 |
+
- 🐦 [X/Twitter: @BitMindAI](https://x.com/BitMindAI)
|
| 97 |
""")
|
| 98 |
|
| 99 |
with gr.Tabs():
|