TY  - CONF
AU  - Simon Jégou
AU  - Michal Drozdzal
AU  - David Vazquez
AU  - Adriana Romero
AU  - Yoshua Bengio
A2  - CVPRW
PY  - 2017//
TI  - The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
BT  - IEEE Conference on Computer Vision and Pattern Recognition Workshops
KW  - Semantic Segmentation
N2  - State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions.Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train.In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets.
UR  - https://ieeexplore.ieee.org/document/8014890
L1  - http://refbase.cvc.uab.es/files/jdv2016.pdf
UR  - http://dx.doi.org/10.1109/CVPRW.2017.156
N1  - MILAB; ADAS; 600.076; 600.085; 601.281
ID  - Simon Jégou2017
ER  -