Summary of Extended Cross-modality United Learning For Unsupervised Visible-infrared Person Re-identification, by Ruixing Wu et al.
Extended Cross-Modality United Learning for Unsupervised Visible-Infrared Person Re-identification
by Ruixing Wu, Yiming Yang, Jiakai He, Haifeng Hu
First submitted to arxiv on: 26 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
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 ECUL framework proposes a novel approach to unsupervised learning visible-infrared person re-identification (USL-VI-ReID) by incorporating EMCC and TSMem modules. The existing methods lack cross-modality clustering, which makes it difficult to perform reliable modality-invariant features learning. The proposed ECUL framework naturally integrates intra-modality clustering, inter-modality clustering, and inter-modality instance selection to establish compact and accurate cross-modality associations while reducing the introduction of noisy labels. This framework shows promising performance and even outperforms certain supervised methods on SYSU-MM01 and RegDB datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary USL-VI-ReID is a way for computers to recognize people in different types of images without being shown any examples first. The problem with current methods is that they don’t do a good job of grouping together similar images from different cameras or sensors. To solve this, researchers proposed a new method called ECUL, which combines three steps: grouping images within each camera, grouping images across cameras, and selecting the most important images to use for training. This helps the computer learn how to recognize people in different types of images more accurately. |
Keywords
» Artificial intelligence » Clustering » Supervised » Unsupervised
