BWhat changed
Proposed compound scaling that jointly balances convolutional-network depth, width and input resolution, then used architecture search to build the EfficientNet model family.
Scientific scope
Proposed compound scaling that jointly balances convolutional-network depth, width and input resolution, then used architecture search to build the EfficientNet model family. Scope limitation: Efficiency and accuracy comparisons are author-reported for specified datasets and hardware; compound scaling is not a claim that EfficientNet dominates all later vision models.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. Efficiency and accuracy comparisons are author-reported for specified datasets and hardware; compound scaling is not a claim that EfficientNet dominates all later vision models.
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.
- Tan and Le: EfficientNet compound scaling for convolutional networks — original paper
- Tan and Le: EfficientNet compound scaling for convolutional networks — company research page
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