Summary of Band-attention Modulated Retnet For Face Forgery Detection, by Zhida Zhang et al.
Band-Attention Modulated RetNet for Face Forgery Detection
by Zhida Zhang, Jie Cao, Wenkui Yang, Qihang Fan, Kai Zhou, Ran He
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Multimedia (cs.MM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Band-Attention modulated RetNet (BAR-Net) is a lightweight network designed to balance the capture of global context and computational complexity in face forgery detection. By introducing self-attention along both spatial axes, BAR-Net maintains spatial priors while easing computational burden. The adaptive frequency Band-Attention Modulation mechanism treats the entire Discrete Cosine Transform spectrogram as a series of frequency bands with learnable weights. This approach empowers the target token to perceive global information by assigning differential attention levels to tokens at varying distances. BAR-Net achieves favorable performance on several face forgery datasets, outperforming current state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary BAR-Net is a new way to detect fake faces. It uses special computers called transformers that can look at lots of information at once. The problem with these transformers is they can get confused when looking at big pictures. To fix this, the researchers added a special feature that helps the computer focus on the right parts of the picture. This makes it better at detecting fake faces than other methods. |
Keywords
» Artificial intelligence » Attention » Self attention » Token
