Method Details

Details for method 'LRR-4x'

name	LRR-4x
challenge	pixel-level semantic labeling
details	We introduce a CNN architecture that reconstructs high-resolution class label predictions from low-resolution feature maps using class-specific basis functions. Our multi-resolution architecture also uses skip connections from higher resolution feature maps to successively refine segment boundaries reconstructed from lower resolution maps. The model used for this submission is based on VGG-16 and it was trained on the training set (2975 images). The segmentation predictions were not post-processed using CRF. (This is a revision of a previous submission in which we didn't use the correct basis functions; the method name changed from 'LLR-4x' to 'LRR-4x')
publication	Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation Golnaz Ghiasi, Charless C. Fowlkes ECCV 2016 http://arxiv.org/abs/1605.02264
project page / code	https://github.com/golnazghiasi/LRR
used Cityscapes data	fine annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	July, 2016
previous submissions	1