SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1611.09326 · 2016

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 24 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
kskim-phd/mfcn pwc_unofficial 1 of 6
ankit-vaghela30/Cilia-Segmentation pwc_unofficial 0 of 9
copy not recorded — 0 of 3
petko-nikolov/pysemseg reimplementation 0 of 3
0bserver07/One-Hundred-Layers-Tiramisu pwc_unofficial 0 of 3
FunctionStatusWhere it lives
center_crop Ran kskim-phd/mfcn/MFCN_SMC/code_MFCN/layers.py
code served (permissive licence) · get_code("9d5555c9ff725b7f")
FCDenseNet103 Not yet run this paper's copy was not recorded; identical code first harvested from bfortuner/pytorch_tiramisu
pointer only · get_code("a31003fad13ae67c")
FCDenseNet57 Not yet run this paper's copy was not recorded; identical code first harvested from bfortuner/pytorch_tiramisu
pointer only · get_code("f1271d09e9ba1ad7")
FCDenseNet67 Not yet run this paper's copy was not recorded; identical code first harvested from bfortuner/pytorch_tiramisu
pointer only · get_code("cfa9b6051f647903")
blur Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/preprocessing.py
code served (permissive licence) · get_code("606293610ee73f36")
bn Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/tiramisu_model.py
code served (permissive licence) · get_code("011e9d1f4a18f0c1")
center_crop Not yet run kskim-phd/mfcn/MFCN_SMC/code_MFCN/mydataset.py
code served (permissive licence) · get_code("2b32f51f5f7b51cc")
center_crop_mask Not yet run kskim-phd/mfcn/MFCN_SMC/code_MFCN/mydataset.py
code served (permissive licence) · get_code("799d1ba8540920a4")
dropout Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/tiramisu_model.py
code served (permissive licence) · get_code("f60d7b457f163df3")
fcdensenet103 Not yet run petko-nikolov/pysemseg/pysemseg/models/densenet.py
pointer only (licence: GPL-3.0) · get_code("a8205d6e6712fbf5")
fcdensenet56 Not yet run petko-nikolov/pysemseg/pysemseg/models/densenet.py
pointer only (licence: GPL-3.0) · get_code("fc05fafe6352aa0c")
fcdensenet67 Not yet run petko-nikolov/pysemseg/pysemseg/models/densenet.py
pointer only (licence: GPL-3.0) · get_code("71b9ef5924a9d9be")
get_JI Not yet run kskim-phd/mfcn/MFCN_SMC/code_MFCN/stage1_conventional_model.py
code served (permissive licence) · get_code("f19ea4f954b9e8d0")
get_JI Not yet run kskim-phd/mfcn/MFCN_SMC/code_MFCN/stage2_patch_wise.py
code served (permissive licence) · get_code("36a022450e439192")
gray2rgb Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/preprocessing.py
code served (permissive licence) · get_code("229fb6fceb2b565a")
load_all_video Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/io_support.py
code served (permissive licence) · get_code("ba25286a61fa1d4f")
load_data Not yet run 0bserver07/One-Hundred-Layers-Tiramisu/camvid_data_loader.py
code served (permissive licence) · get_code("ee76790f2e23db5a")
load_img Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/io_support.py
code served (permissive licence) · get_code("71d2f0c11ca47487")
load_video Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/io_support.py
code served (permissive licence) · get_code("6b7485606e8ec4b4")
normalized Not yet run 0bserver07/One-Hundred-Layers-Tiramisu/helper.py
code served (permissive licence) · get_code("600dd344d089e843")
one_hot_it Not yet run 0bserver07/One-Hundred-Layers-Tiramisu/helper.py
code served (permissive licence) · get_code("8eb260280ed17f0f")
post_processing Not yet run kskim-phd/mfcn/MFCN_SMC/code_MFCN/stage1_conventional_model.py
code served (permissive licence) · get_code("65d0d9510aa373d4")
relu Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/tiramisu_model.py
code served (permissive licence) · get_code("a5b43c4ed0ec9709")
threshold Not yet run ankit-vaghela30/Cilia-Segmentation/hastings/preprocessing.py
code served (permissive licence) · get_code("cc07c5438fa01645")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. Code to reproduce the experiments is available here : https://github.com/SimJeg/FC-DenseNet/blob/master/train.py

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1611.09326")
get_code_for_paper("1611.09326")
have("1611.09326")

Connect an agent — have() is free.