Method Details

Details for method 'DPC'

name	DPC
challenge	pixel-level semantic labeling
details	In this work we explore the construction of meta-learning techniques for dense image prediction focused on the tasks of scene parsing. Constructing viable search spaces in this domain is challenging because of the multi-scale representation of visual information and the necessity to operate on high resolution imagery. Based on a survey of techniques in dense image prediction, we construct a recursive search space and demonstrate that even with efficient random search, we can identify architectures that achieve state-of-the-art performance. Additionally, the resulting architecture (called DPC for Dense Prediction Cell) is more computationally efficient, requiring half the parameters and half the computational cost as previous state of the art systems.
publication	Searching for Efficient Multi-Scale Architectures for Dense Image Prediction Liang-Chieh Chen, Maxwell D. Collins, Yukun Zhu, George Papandreou, Barret Zoph, Florian Schroff, Hartwig Adam, Jonathon Shlens NIPS 2018 https://arxiv.org/abs/1809.04184
project page / code	https://github.com/tensorflow/models/tree/master/research/deeplab
used Cityscapes data	fine annotations, coarse annotations
used external data	ImageNet, COCO
runtime	n/a
subsampling	no
submission date	May, 2018
previous submissions