This is the official implementation of TRN on MinVIS.

• Temporal Reduce Network to Speed Up Video Instance Segmentation models.
• Support major video instance segmentation datasets: YouTubeVIS 2019/2021, Occluded VIS (OVIS).

See installation instructions.

See Preparing Datasets for TRN.

See Getting Started with TRN.

Trained models are available for download in the TRN Model Zoo.

The majority of TRN is made available under the Nvidia Source Code License-NC. The trained models in the TRN Model Zoo are made available under the CC BY-NC-SA 4.0 License.

Portions of the project are available under separate license terms: Mask2Former is licensed under a MIT License. Swin-Transformer-Semantic-Segmentation is licensed under the MIT License, Deformable-DETR is licensed under the Apache-2.0 License.

This repo is largely based on Mask2Former (https://github.com/facebookresearch/Mask2Former) and MinVIS (https://github.com/NVlabs/MinVIS).