Skip to main content

> ML_LITERATURE // SZEGEDY-2015-GOING-DEEPER-WITH-CONVOLUTIONS-GOOGLENET_v1.0

Going Deeper with Convolutions (GoogLeNet / Inception)

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich · IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

seminal-architecture2015industry-standardthirdPartyReproduced
DOI: 10.1109/CVPR.2015.7298594Back to Literature

Principal Contribution

Designed multi-scale Inception modules executing parallel 1x1, 3x3, and 5x5 convolutions with 1x1 bottlenecks to dramatically reduce parameter counts.

Operational Relevance

Serves as qualified reference for implementing task-image-classification 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: