Hugging Face's logo

HPAI-BSC
/
SuSy

Image Classification
Transformers
vision
synthetic image detection
Inference Endpoints
Model card Files Community
dariog commited on
Commit
6fc2104
路
verified 路
1 Parent(s): 54d4d55

Fix figures

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -15,10 +15,12 @@ pipeline_tag: image-classification
15
 
16
  # SuSy - Synthetic Image Detector
17
 
18
- ![susy-logo](susy_logo.jpeg)
 
19
 
20
  - **Repository:** https://github.com/HPAI-BSC/SuSy
21
  - **Dataset:** https://huggingface.co/datasets/HPAI-BSC/SuSy-Dataset
 
22
 
23
  ## Model Details
24
 
@@ -26,7 +28,7 @@ pipeline_tag: image-classification
26
 
27
  SuSy is a Spatial-Based Synthetic Image Detection and Recognition Model, designed and trained to detect synthetic images and attribute them to a generative model (i.e., two StableDiffusion models, two Midjourney versions and DALL路E 3). The model takes image patches of size 224x224 as input, and outputs the probability of the image being authentic or having been created by each of the aforementioned generative models.
28
 
29
- ![model-architecture](model_architecture.png)
30
 
31
  The model is based on a CNN architecture and is trained using a supervised learning approach. It's design is based on [previous work](https://upcommons.upc.edu/handle/2117/395959), originally intended for video superresolution detection, adapted here for the tasks of synthetic image detection and recognition. The architecture consists of two modules: a feature extractor and a multi-layer perceptron (MLP), as it's quite light weight. SuSy has a total of 12.7M parameters, with the feature extractor accounting for 12.5M parameters and the MLP accounting for the remaining 197K.
32
 
 
15
 
16
  # SuSy - Synthetic Image Detector
17
 
18
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/62f7a16192950415b637e201/NobqlpFbFkTyBi1LsT9JE.png" alt="image" width="300" height="auto">
19
+
20
 
21
  - **Repository:** https://github.com/HPAI-BSC/SuSy
22
  - **Dataset:** https://huggingface.co/datasets/HPAI-BSC/SuSy-Dataset
23
+ - **Paper:** TBD
24
 
25
  ## Model Details
26
 
 
28
 
29
  SuSy is a Spatial-Based Synthetic Image Detection and Recognition Model, designed and trained to detect synthetic images and attribute them to a generative model (i.e., two StableDiffusion models, two Midjourney versions and DALL路E 3). The model takes image patches of size 224x224 as input, and outputs the probability of the image being authentic or having been created by each of the aforementioned generative models.
30
 
31
+ <img src="model_architecture.png" alt="image" width="900" height="auto">
32
 
33
  The model is based on a CNN architecture and is trained using a supervised learning approach. It's design is based on [previous work](https://upcommons.upc.edu/handle/2117/395959), originally intended for video superresolution detection, adapted here for the tasks of synthetic image detection and recognition. The architecture consists of two modules: a feature extractor and a multi-layer perceptron (MLP), as it's quite light weight. SuSy has a total of 12.7M parameters, with the feature extractor accounting for 12.5M parameters and the MLP accounting for the remaining 197K.
34