add PASCAL-Context FCNs

The usual FCN-32/16/8s on the 59 class task of the PASCAL-Context full
object and scene labeling of PASCAL VOC 2010.

README.md

@@ -48,9 +48,8 @@ These models demonstrate FCNs for multi-task output.
 This will be corrected soon.
 The evaluation of the geometric classes is fine.
 
-**The following models have not yet been ported to master and trained with the latest settings. Check back soon.**
+**PASCAL-Context models**: trained online with high momentum on an object and scene labeling of PASCAL VOC.
 
-PASCAL-Context models including architecture definition, solver configuration, and bare-bones solving script (fine-tuned from the ILSVRC-trained VGG-16 model):
-* [FCN-32s PASCAL-Context](https://gist.github.com/shelhamer/80667189b218ad570e82#file-readme-md): single stream, 32 pixel prediction stride version
-* [FCN-16s PASCAL-Context](https://gist.github.com/shelhamer/08652f2ba191f64e619a#file-readme-md): two stream, 16 pixel prediction stride version
-* [FCN-8s PASCAL-Context](https://gist.github.com/shelhamer/91eece041c19ff8968ee#file-readme-md): three stream, 8 pixel prediction stride version
+* [FCN-32s PASCAL-Context](pascalcontext-fcn32s): single stream, 32 pixel prediction stride net
+* [FCN-16s PASCAL-Context](pascalcontext-fcn16s): two stream, 16 pixel prediction stride net
+* [FCN-8s PASCAL-Context](pascalcontext-fcn8s): three stream, 8 pixel prediction stride net

data/pascal-context/README.md

@@ -0,0 +1,19 @@
+# PASCAL-Context
+
+PASCAL-Context is a full object and scene labeling of PASCAL VOC 2010.
+It includes both object (cat, dog, ...) and surface (sky, grass, ...) classes.
+
+We follow the 59 class task defined by
+
+> The Role of Context for Object Detection and Semantic Segmentation in the Wild.
+Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, and Alan Yuille.
+CVPR 2014
+
+which selects the 59 most common classes for learning and evaluation.
+
+Refer to `classes-59.txt` for the listing of classes in model output order.
+Refer to `../pascalcontext_layers.py` for the Python data layer for this dataset.
+
+Note that care must be taken to map the raw class annotations into the 59 class task, as handled by our data layer.
+
+See the dataset site: http://www.cs.stanford.edu/~roozbeh/pascal-context/