Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

NeurIPS 2018 Liang-Chieh ChenMaxwell D. CollinsYukun ZhuGeorge PapandreouBarret ZophFlorian SchroffHartwig AdamJonathon Shlens

The design of neural network architectures is an important component for achieving state-of-the-art performance with machine learning systems across a broad array of tasks. Much work has endeavored to design and build architectures automatically through clever construction of a search space paired with simple learning algorithms... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Semantic Segmentation Cityscapes test Dense Prediction Cell Mean IoU (class) 82.7% # 5
Semantic Segmentation PASCAL VOC 2012 test DPC Mean IoU 87.9% # 2