Awesome
Awesome-Panoptic-Segmentation
If you have any problems, suggestions or improvements, please submit the issue or PR.
<h1>Content</h1> <ul> <li>Datasets</li> <li>Papers with codes</li> <ul> <li>2021</li> <li>2020</li> <li>2019</li> <li>2018</li> </ul> </ul> <h1>Datasets</h1> <ul> <li><p><a href="https://www.mapillary.com/dataset/vistas">Mapillary Vistas</a></p></li> <li><p><a href="http://www.cvlibs.net/datasets/kitti/">KITTI</a></p></li> <li><p><a href="http://www.semantic-kitti.org">SemanticKITTI</a></p></li> <li><p><a href="http://vision.middlebury.edu/stereo/data/">Middlebury Stereo</a></p></li> <li><p><a href="https://www.cityscapes-dataset.com/">Cityscapes</a></p></li> <li><p><a href="https://cocodataset.org/#panoptic-2018">COCO panoptic task</a></p></li> <li><p><a href="http://host.robots.ox.ac.uk/pascal/VOC/">PSCAL VOC 2012</a></p></li> <li><p><a href="http://groups.csail.mit.edu/vision/datasets/ADE20K/">ADE20K</a></p></li> <li><p><a href="https://synthia-dataset.net">SYNTHIA</a></p></li> <li><p><a href="https://ieeexplore.ieee.org/document/7872382">TCGA-KUMAR</a></p></li> <li><p><a href="https://pubmed.ncbi.nlm.nih.gov/30716022/">TNBC</a></p></li> <li><p><a href="https://data.broadinstitute.org/bbbc/BBBC039/">BBBC039V1</a></p></li> </ul> <h1>Paper with code</h1><b>2021 :</b>
<ul> <li>PPS: Wild Panoramic Panoptic Segmentation dataset [<a href="https://github.com/alexanderjaus/PPS" rel="nofollow">Code</a>]</li> </ul><b>2020:</b>
<ul> <li>Panoptic-deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmentation [<a href="https://github.com/bowenc0221/panoptic-deeplab?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Learning instance occlusion for panoptic segmentation [<a href="https://github.com/jlazarow/learning_instance_occlusion?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Efficientps: Efficient panoptic segmentation [<a href="https://github.com/DeepSceneSeg/EfficientPS?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation [<a href="https://github.com/lironui/Linear-Attention-Mechanism?utm_source=catalyzex.com " rel="nofollow">Code</a>]</li> <li>Stable and expressive recurrent vision models [<a href="https://github.com/c-rbp?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>DESC: Domain Adaptation for Depth Estimation via Semantic Consistency [<a href="https://github.com/alopezgit/DESC?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges [<a href="https://github.com/QingyongHu/SensatUrban?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Context Prior for Scene Segmentation [<a href="https://github.com/DengPingFan/CODToolbox?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation [<a href="https://github.com/csrhddlam/axial-deeplab" rel="nofollow">Code</a>]</li> <li>Video Panoptic Segmentation [<a href="https://github.com/mcahny/vps?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding [<a href="https://github.com/tue-mps/panoptic_parts?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> </ul><b>2019:</b>
<ul> <li>Panoptic segmentation[<a href="https://github.com/kdethoor/panoptictorch?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Upsnet: A unified panoptic segmentation network [<a href="https://github.com/uber-research/UPSNet?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Panoptic feature pyramid networks [<a href="https://github.com/facebookresearch/detectron2?utm_source=catalyzex.com " rel="nofollow">Code</a>]</li> <li>Sognet: Scene overlap graph network for panoptic segmentation [<a href="https://github.com/LaoYang1994/SOGNet?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Single network panoptic segmentation for street scene understanding [<a href="https://github.com/DdeGeus/single-network-panoptic-segmentation?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Generator evaluator-selector net: a modular approach for panoptic segmentation [<a href="https://github.com/sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Seamless scene segmentation [<a href="https://github.com/mapillary/seamseg?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Adaptis: Adaptive instance selection network [<a href="https://github.com/saic-vul/adaptis?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>Associatively segmenting instances and semantics in point clouds [<a href="https://github.com/WXinlong/ASIS?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>MOTS: Multi-object tracking and segmentation [<a href="https://github.com/VisualComputingInstitute/TrackR-CNN?utm_source=catalyzex.com" rel="nofollow">Code</a>]</li> <li>AdaptIS: Adaptive Instance Selection Network [<a href="https://github.com/saic-vul/adaptis" rel="nofollow">Code</a>]</li> <li>ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation [<a href="https://github.com/sacmehta/ESPNet" rel="nofollow">Code</a>]</li> <li>SpatialFlow: Bridging All Tasks for Panoptic Segmentation [<a href="https://github.com/chensnathan/SpatialFlow" rel="nofollow">Code</a>]</li> <li>Bipartite Conditional Random Fields for Panoptic Segmentation [<a href="https://github.com/sahan-liyanaarachchi/bcrf-detectron" rel="nofollow">Code</a>]</li> <li>Vargnet: Variable group convolutional neural network for efficient embedded computing [<a href="https://www.catalyzex.com/redirect?url=https://github.com/zma-c-137/VarGFaceNet" rel="nofollow">Code</a>]</li> <li>Weakly supervised cell instance segmentation by propagating from detection response [<a href="https://www.catalyzex.com/redirect?url=https://github.com/naivete5656/WSISPDR" rel="nofollow">Code</a>]</li> <li>Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images [<a href="https://www.catalyzex.com/redirect?url=https://github.com/vqdang/xy_net" rel="nofollow">Code</a>]</li> <li>Woodscape: A multi-task, multi-camera fisheye dataset for autonomous driving [<a href="https://www.catalyzex.com/redirect?url=https://github.com/valeoai/WoodScape" rel="nofollow">Code</a>]</li> <li>Harvesting Information from Captions for Weakly Supervised Semantic Segmentation [<a href="https://www.catalyzex.com/redirect?url=https://github.com/kevinlee9/Semantic-Segmentation" rel="nofollow">Code</a>]</li> <li>Object-contextual representations for semantic segmentation [<a href="https://www.catalyzex.com/redirect?url=https://github.com/openseg-group/openseg.pytorch" rel="nofollow">Code</a>]</li> <li>A hierarchical probabilistic u-net for modeling multi-scale ambiguities [<a href="https://www.catalyzex.com/redirect?url=https://github.com/cbailes/awesome-ai-cancer" rel="nofollow">Code</a>]</li> <li>Parsing r-cnn for instance-level human analysis [<a href="https://www.catalyzex.com/redirect?url=https://github.com/soeaver/Parsing-R-CNN " rel="nofollow">Code</a>]</li> </ul><b>2018:</b>
<ul> <li>ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation [<a href="https://github.com/sacmehta/ESPNet/" rel="nofollow">Code</a>]</li> <li>Weakly- and Semi-Supervised Panoptic Segmentation [<a href="https://github.com/qizhuli/Weakly-Supervised-Panoptic-Segmentation" rel="nofollow">Code</a>]</li> <li>Effective use of synthetic data for urban scene semantic segmentationC [<a href="https://www.catalyzex.com/redirect?url=https://github.com/fatemehSLH/VEIS" rel="nofollow">Code</a>]</li> <h1>Citation</h1> <div class="snippet-clipboard-content position-relative" data-snippet-clipboard-copy-content="@article{elharrouss2021drone, title={Drone-SCNet: Scaled Cascade Network for Crowd Counting on Drone Images}, author={Elharrouss, Omar and Almaadeed, Noor and Abualsaud, Khalid and Al-Ali, Ali and Mohamed, Amr and Khattab, Tamer and Al-Maadeed, Somaya}, journal={IEEE Transactions on Aerospace and Electronic Systems}, year={2021}, publisher={IEEE} } "><pre><code>@article{elharrouss2021panoptic, title={Panoptic Segmentation: A Review}, author={Elharrouss, Omar and Al-Maadeed, Somaya and Subramanian, Nandhini and Ottakath, Najmath and Almaadeed, Noor and Himeur, Yassine}, journal={arXiv preprint arXiv:2111.10250}, year={2021}}
</ul>