Hugging Face's logo

AP6621
/
AI_generated_image_detection

Image Classification
English
densenet
ai-generated-content
human-created-content
model-card
Model card Files Community
AI_generated_image_detection / README.md
Alok Pandey
Update README.md
ffa0de3 verified
preview code
|
raw
history blame
3.61 kB
metadata
language: en
license: mit
tags:
  - image-classification
  - densenet
  - ai-generated-content
  - human-created-content
  - model-card

Model Card: Fine-tuned DenseNet for Image Classification

Model Overview

This fine-tuned DenseNet121 model is designed to classify images into the following categories:

  1. DALL-E Generated Images
  2. Human-Created Images
  3. Other AI-Generated Images

The model is ideal for detecting AI-generated content, particularly useful in creative fields such as art and design.

Use Cases

  • AI Art Detection: Identifies whether an image was generated by AI or created by a human.
  • Content Moderation: Useful in media, art, and design industries where distinguishing AI-generated content is essential.
  • Educational Purposes: Useful for exploring the differences between AI and human-generated content.

Model Performance

  • Accuracy: 95% on the validation dataset.
  • Loss: 0.0552 after 15 epochs of training.

Training Details

  • Base Model: DenseNet121, pretrained on ImageNet.
  • Optimizer: Adam with a learning rate of 0.0001.
  • Loss Function: Cross-Entropy Loss.
  • Batch Size: 32
  • Epochs: 15

The model was fine-tuned using data augmentation techniques like random flips, rotations, and color jittering to improve robustness.

To support .png files and ensure that the images are rendered properly, you need to reference the correct file format in the image URLs. Additionally, you should use the appropriate image path for your hosting platform (like Hugging Face).

Updated Model Card with Support for .png Images:

Training Metrics

1. Loss Over Epochs

Loss Over Epochs
This graph shows the decrease in loss over 15 epochs, indicating the model's improved ability to fit the data.

2. Accuracy Over Epochs

Accuracy Over Epochs
This graph shows the increase in accuracy, reflecting the model's growing ability to correctly classify images.

Model Output Samples

Here are some examples of the model's predictions on various images:

Sample 1: Human-Created Image

Sample 1
Predicted: Human-Created

Sample 2: DALL-E Generated Image

Sample 2
Predicted: DALL-E Generated

Sample 3: Other AI-Generated Image

Sample 3
Predicted: Other AI-Generated

Model Architecture

  • Feature Extractor: DenseNet121 with frozen layers to retain general features from ImageNet.
  • Classifier: A fully connected layer with 3 output nodes, one for each class (DALL-E, Human-Created, Other AI).

Limitations

  • Data Bias: The model's performance is dependent on the balance and diversity of the training dataset.
  • Generalization: Further testing on more diverse datasets is recommended to validate the model’s performance across different domains and types of images.

Model Download

You can download the fine-tuned DenseNet121 model using the following link:
Download the Model

References

For more information on DenseNet, refer to the original research paper:
Densely Connected Convolutional Networks (DenseNet)