Unofficial implementation of MaX-DeepLab for Instance Segmentation: https://arxiv.org/abs/2012.00759v1.
Only the MaX-DeepLab-S architecture is putatively implemented. Primarily, this code is intended as a reference; I can't make any guarantees that it will reproduce the results of the paper.
- Axial Attention block
- Dual Path Transformer block
- MaX-DeepLab-S architecture
- Hungarian Matcher
- PQ-style loss
- Auxiliary losses (Instance discrimination, Mask-ID cross-entropy, Semantic Segmentation)
- Coco Panoptic Dataset
- Simple inference
See example.ipynb.