VGG: small-filter stacks and systematic deep visual classifiers

What changed

Systematically evaluated convolutional depth using repeated small3×3filters and a common architecture, demonstrating effective16–19weight-layer visual classifiers.

Scientific scope

Systematically evaluated convolutional depth using repeated small3×3filters and a common architecture, demonstrating effective16–19weight-layer visual classifiers. Inherits CNNs and small-filter predecessors, not their invention.2014preprint/competition result precedes2015conference; classification/localization placements differ. Parameter comparisons for convolutional stacks do not imply small total VGG memory or universal optimal depth.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits CNNs and small-filter predecessors, not their invention.2014preprint/competition result precedes2015conference; classification/localization placements differ. Parameter comparisons for convolutional stacks do not imply small total VGG memory or universal optimal depth.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Very Deep Convolutional Networks for Large-Scale Image Recognition

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction