damo-cv/TransReID
A transformer-based deep learning model for object re-identification achieving state-of-the-art on person and vehicle re-ID benchmarks.
Not currently ranked — collecting fresh signals.
star history
TransReID is an official implementation of an ICCV 2021 paper that applies Vision Transformer architecture to object re-identification tasks. The model handles person re-ID and vehicle re-ID using transformer encoders with specialized loss functions and training pipelines. It provides code for training and evaluation on standard benchmarks including Market-1501, MSMT17, DukeMTMC-reID, VehicleID, and VeRi-776.
Frequently asked
- What is damo-cv/TransReID?
- A transformer-based deep learning model for object re-identification achieving state-of-the-art on person and vehicle re-ID benchmarks.
- Is TransReID open source?
- Yes — damo-cv/TransReID is open source, released under the MIT license.
- What language is TransReID written in?
- damo-cv/TransReID is primarily written in Python.
- How popular is TransReID?
- damo-cv/TransReID has 1k stars on GitHub.
- Where can I find TransReID?
- damo-cv/TransReID is on GitHub at https://github.com/damo-cv/TransReID.