Skip to main content

> ML_LITERATURE // SIMONYAN-2014-VERY-DEEP-CONVOLUTIONAL-NETWORKS-VGG_v1.0

Very Deep Convolutional Networks for Large-Scale Image Recognition (VGG)

Karen Simonyan, Andrew Zisserman · International Conference on Learning Representations (ICLR) (2014)

seminal-architecture2014industry-standardthirdPartyReproduced
arXiv:1409.1556Back to Literature

Principal Contribution

Showed that pushing network depth up to 16-19 layers using uniform, small 3x3 convolution filters consistently improves representation quality.

Operational Relevance

Serves as qualified reference for implementing task-image-classification, task-feature-extraction 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: