PofoliaShared via Pofolia

IEEE Transactions on Pattern Analysis and Machine Intelligence· 2019Q1

Squeeze-and-Excitation Networks

Jie Hu, Li Shen, Samuel Albanie, Gang Sun et al.

Short summary

This paper introduces the "Squeeze-and-Excitation" (SE) block, a novel architectural unit for Convolutional Neural Networks (CNNs) that adaptively recalibrates channel-wise feature responses by modeling interdependencies between channels.

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 open

Field: Atomic and Molecular Physics, and Optics

Atomic and Molecular Physics, and OpticsPhysics and Astronomy