Skip to main content

> ML_LITERATURE // RADOSAVOVIC-2020-DESIGNING-NETWORK-DESIGN-SPACES-REGNET_v1.0

Designing Network Design Spaces (RegNet)

Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár · IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

seminal-architecture2020foundationalthirdPartyReproduced
DOI: 10.1109/CVPR42600.2020.01044Back to Literature

Principal Contribution

Pioneered statistical design space exploration rather than individual instance search, discovering the quantized linear parameter rule of RegNet matching EfficientNet speed and accuracy.

Operational Relevance

Serves as qualified reference for deploying task-image-classification in production.

Assumptions

  • Spatial feature coherence and data manifold structure adhere to continuous representation hypotheses

Limitations

  • Computational complexity scales with spatial resolution and parameter capacity

Connected Algorithms, Architectures & Tools

Related Algorithms:
Related Architectures:
Implementing Libraries: