Summary of Efficient Fine-tuning with Domain Adaptation For Privacy-preserving Vision Transformer, by Teru Nagamori et al.
Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
by Teru Nagamori, Sayaka Shiota, Hitoshi Kiya
First submitted to arxiv on: 10 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 This paper proposes a novel approach for privacy-preserving deep neural networks (DNNs) that utilizes the Vision Transformer (ViT). The method enables training and testing with visually protected images, while avoiding performance degradation caused by image encryption. A domain adaptation technique is employed to fine-tune ViT with encrypted images, leading to improved classification accuracy on CIFAR-10 and ImageNet datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make sure that deep learning models don’t accidentally reveal personal information. It’s like putting a special filter on the pictures so they can’t be understood by anyone who shouldn’t see them. The team came up with a way to train these models using encrypted images, which is important because regular methods would get affected by the encryption. They tested it and found that their method works better than others for image classification tasks. |
Keywords
* Artificial intelligence * Classification * Deep learning * Domain adaptation * Image classification * Vision transformer * Vit
