init

README.md

@@ -1,3 +1,33 @@
 ---
 license: afl-3.0
 ---
+
+## DeepLab v3 plus - ResNet101 model trained on MUAD dataset
+This is a DeepLab v3 plus model with ResNet101 as the backbone trained on MUAD dataset. The training is based on PyTorch.
+
+MUAD is the a synthetic dataset with multiple uncertainties for autonomous driving [[Paper]](https://arxiv.org/abs/2203.01437) [[Website]](https://muad-dataset.github.io/) [[Github]](https://github.com/ENSTA-U2IS/MUAD-Dataset).
+
+### ICCV UNCV 2023 | MUAD challenge
+MUAD challenge is now on board on the Codalab platform for uncertainty estimation in semantic segmentation. This challenge is hosted in conjunction with the [ICCV 2023](https://iccv2023.thecvf.com/) workshop, [Uncertainty Quantification for Computer Vision (UNCV)](https://uncv2023.github.io/). Go and have a try! 🚀 🚀 🚀 [[Challenge link]](https://codalab.lisn.upsaclay.fr/competitions/8007)
+
+### Reference
+If you find this work useful for your research, please consider citing our paper:
+```
+@inproceedings{franchi22bmvc,
+  title = {MUAD: Multiple Uncertainties for Autonomous Driving benchmark for multiple uncertainty types and tasks},
+  author = {Gianni Franchi and Xuanlong Yu and Andrei Bursuc and Angel Tena and Rémi Kazmierczak and Severine Dubuisson and Emanuel Aldea and David Filliat},
+  booktitle = {33rd British Machine Vision Conference, {BMVC}},
+  year = {2022}
+}
+```
+```
+@inproceedings{deeplabv3plus2018,
+  title = {Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
+  author = {Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
+  booktitle = {ECCV},
+  year = {2018}
+}
+```
+
+### Copyright
+Copyright for MUAD Dataset is owned by Université Paris-Saclay (SATIE Laboratory, Gif-sur-Yvette, FR) and ENSTA Paris (U2IS Laboratory, Palaiseau, FR).

best_deeplabv3plus_resnet101_muad.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1567729c4a48ed4b79cd8a46e6b84f18520bc38a788401517f8ff6e354868c63
+size 470827449