Methods > Computer Vision > Convolutional Neural Networks

SpineNet

Introduced by Du et al. in SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
 
Edit

SpineNet is a convolutional neural network backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.

Source: SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
Paper Code Snippet

Latest Papers

PAPER DATE
Efficient Scale-Permuted Backbone with Learned Resource Distribution
Xianzhi Du • Tsung-Yi Lin • Pengchong Jin • Yin Cui • Mingxing Tan • Quoc Le • Xiaodan Song
2020-10-22
Rethinking Pre-training and Self-training
| Barret Zoph • Golnaz Ghiasi • Tsung-Yi Lin • Yin Cui • Hanxiao Liu • Ekin D. Cubuk • Quoc V. Le
# 3 OBJECT DETECTION ON COCO TEST-DEV
2020-06-11
Evolving Normalization-Activation Layers
| Hanxiao Liu • Andrew Brock • Karen Simonyan • Quoc V. Le
2020-04-06
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
| Xianzhi Du • Tsung-Yi Lin • Pengchong Jin • Golnaz Ghiasi • Mingxing Tan • Yin Cui • Quoc V. Le • Xiaodan Song
# 2 INSTANCE SEGMENTATION ON COCO MINIVAL
2019-12-10

Tasks

TASK PAPERS SHARE
Object Detection 3 25.00%
Semantic Segmentation 3 25.00%
Image Classification 2 16.67%
Instance Segmentation 2 16.67%
Image Generation 1 8.33%
Real-Time Object Detection 1 8.33%

Categories
Add Remove

Contact us on: [email protected]. Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Privacy Cookies policy