> ML_LITERATURE // LIU-2021-SWIN-TRANSFORMER-HIERARCHICAL-VISION-TRANSFORMER_v1.0
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo · IEEE International Conference on Computer Vision (ICCV) (2021)
seminal-architecture2021industry-standardthirdPartyReproduced
Principal Contribution
Introduced shifted window self-attention delivering linear computational complexity with respect to image size while maintaining cross-window connections.
Operational Relevance
Serves as qualified reference for implementing task-image-classification, task-object-detection, task-image-segmentation in production systems.
Assumptions
- Underlying spatio-temporal continuity and domain distributional stability hold
Limitations
- Performance scaling and computational footprint depend on receptive field depth, sequence length, and resolution
Connected Algorithms, Architectures & Tools
Related Algorithms:
Related Architectures:
Implementing Libraries: