Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
CNN architectures have terrific recognition performance
but rely on spatial pooling which makes it difficult to adapt
them to tasks that require dense, pixel-accurate labeling.
This paper makes two contributions: (1) We demonstrate that
while the apparent spatial resolution of convolutional feature
maps is low, the high-dimensional feature representation
contains significant sub-pixel localization information.
(2) We describe a multi-resolution reconstruction architecture
based on a Laplacian pyramid that uses skip connections
from higher resolution feature maps and multiplicative
gating to successively refine segment boundaries reconstructed
from lower-resolution maps. This approach yields
state-of-the-art semantic segmentation results on the PASCAL VOC
and Cityscapes segmentation benchmarks without resorting to
more complex random-field inference or instance detection
driven architectures.
Download: pdf
Text Reference
Golnaz Ghiasi and Charless Fowlkes. Laplacian pyramid reconstruction and refinement for semantic segmentation. In ECCV. 2016.BibTeX Reference
@inproceedings{GhiasiF_ECCV_2016,AUTHOR = "Ghiasi, Golnaz and Fowlkes, Charless",
TITLE = "Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation",
BOOKTITLE = "ECCV",
YEAR = "2016",
tag = "grouping,object_recognision"
}