Summary of Learning Disentangled Representation For Robust Person Re-identification, by Chanho Eom et al.
Learning Disentangled Representation for Robust Person Re-identification
by Chanho Eom, Bumsub Ham
First submitted to arxiv on: 26 Oct 2019
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: None
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 tackles the problem of person re-identification (reID), which involves retrieving person images from a large dataset given a query image. Recent methods focus on learning discriminative features, but this approach is limited to handling specific factors of variation, such as human pose. To overcome this limitation, the authors propose disentangling identity-related and -unrelated features from person images using a generative adversarial network called IS-GAN. This approach factorizes features without requiring auxiliary information. The paper also introduces an identity-shuffling technique to regularize the disentangled features. Experimental results show that IS-GAN outperforms state-of-the-art methods on standard reID benchmarks, including Market-1501, CUHK03, and DukeMTMC-reID. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers want to find a way to easily identify people in pictures. They’re trying to solve this problem by learning what makes each person unique and what doesn’t change about them. They created a new computer program that can separate these things out, which helps it recognize people better. This is important because it can be used for tasks like security cameras recognizing the same person over time. |
Keywords
* Artificial intelligence * Gan * Generative adversarial network
