· 2017
Aggregated Residual Transformations for Deep Neural Networks
- 11,907citations
- 2017year
Short summary
A new modular network architecture, ResNeXt, improves image classification accuracy by introducing 'cardinality' (the number of parallel transformation branches) as a key hyper-parameter, outperforming depth and width increases.
AI-generated from the title and abstract; the full text is not read.
TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app
The rest is in the Pofolia app
Takeaways, key points and questions to the paper; new summaries every day for your field. Free.
Sign in on the web to openField: Artificial Intelligence
Artificial IntelligenceComputer Science