NVlabs/DG-Net
A deep learning system for person re-identification that jointly trains discriminative and generative models.
Not currently ranked — collecting fresh signals.
star history
DG-Net is a computer vision research system that performs person re-identification using joint discriminative and generative learning. It employs a deep neural network architecture to learn discriminative embeddings for matching person images across different camera views while simultaneously generating synthetic images for data augmentation. The system is implemented in PyTorch and achieves state-of-the-art results on standard re-identification benchmarks including Market-1501, DukeMTMC-ReID, and MSMT17.
Frequently asked
- What is NVlabs/DG-Net?
- A deep learning system for person re-identification that jointly trains discriminative and generative models.
- Is DG-Net open source?
- Yes — NVlabs/DG-Net is an open-source project tracked on heatdrop.
- What language is DG-Net written in?
- NVlabs/DG-Net is primarily written in Python.
- How popular is DG-Net?
- NVlabs/DG-Net has 1.3k stars on GitHub.
- Where can I find DG-Net?
- NVlabs/DG-Net is on GitHub at https://github.com/NVlabs/DG-Net.