Summary of Semantic Data Augmentation For Long-tailed Facial Expression Recognition, by Zijian Li et al.
Semantic Data Augmentation for Long-tailed Facial Expression Recognition
by Zijian Li, Yan Wang, Bowen Guan, JianKai Yin
First submitted to arxiv on: 26 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 novel semantic augmentation method for Long-Tailed Recognition tasks introduces randomness into the encoding of source data in the latent space of VAE-GAN to generate new samples, which are then used to balance the long-tailed distribution in facial expression recognition. This method can be applied not only to FER tasks but also to more diverse data-hungry scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a way to make facial expressions easier to recognize in real-world situations by generating new training samples that look like they were taken from the same people and camera angles as the ones used to train the model. This helps the model learn to recognize faces better, even when it’s only shown a few examples of certain facial expressions. |
Keywords
» Artificial intelligence » Gan » Latent space
