- 05 4月, 2018 1 次提交
-
-
由 Evan Shelhamer 提交于
link to our preparation of the dataset with converted depth in the format of Gupta et al. '13
-
- 25 1月, 2018 1 次提交
-
-
由 Evan Shelhamer 提交于
-
- 19 10月, 2016 1 次提交
-
-
由 Evan Shelhamer 提交于
-
- 10 9月, 2016 1 次提交
-
-
由 Evan Shelhamer 提交于
-
- 12 8月, 2016 1 次提交
-
-
由 Evan Shelhamer 提交于
-
- 16 6月, 2016 1 次提交
-
-
由 Evan Shelhamer 提交于
-
- 20 5月, 2016 5 次提交
-
-
由 Evan Shelhamer 提交于
The usual FCN-32/16/8s on the 59 class task of the PASCAL-Context full object and scene labeling of PASCAL VOC 2010.
-
由 Evan Shelhamer 提交于
These nets are jointly trained for segmentation of semantic and geometric classes since this dataset includes annotations for both. - FCN-32s SIFT Flow - FCN-16s SIFT Flow - FCN-8s SIFT Flow TODO: fix semantic class evaluation for this dataset, which requires special care since there are missing classes in the test set.
-
由 Evan Shelhamer 提交于
- FCN-32s Color: FCN-32s arch on BGR input - FCN-32s HHA: FCN-32s arch on HHA input - FCN-32s Color-Depth (early): early fusion for BGR-D input - FCN-32s Color-HHA (late): late fusion of FCN-32s Color + FCN-32s HHA
-
由 Evan Shelhamer 提交于
-
由 Evan Shelhamer 提交于
-
- 22 4月, 2016 1 次提交
-
-
由 Evan Shelhamer 提交于
The SBD train and VOC 2011 segval splits intersect, so the paper reports validation scores for the non-intersecting part of SBD train and seg11val which we call "seg11valid"
-