Szegedy and colleagues: Inception-v3 convolutional architecture

What changed

Improved Inception-style image classifiers using factorized convolutions and regularization to use computation more efficiently.

Scientific scope

Improved Inception-style image classifiers using factorized convolutions and regularization to use computation more efficiently. Scope limitation: First preprint 2015; year follows CVPR 2016. This is an Inception architecture refinement, not the original convolutional network.

Evidence

The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. First preprint 2015; year follows CVPR 2016. This is an Inception architecture refinement, not the original convolutional network.

Contributors

• The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.

• Szegedy and colleagues: Inception-v3 convolutional architecture — original paper
• Szegedy and colleagues: Inception-v3 convolutional architecture — official company source

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