└── README.md /README.md: -------------------------------------------------------------------------------- 1 | 2 | # Interactive Image Segmentation 3 | 4 | ## Deep learning approach 5 | 6 | ### click & scribble 7 | - [Deep Interactive Object Selection](https://arxiv.org/pdf/1603.04042.pdf) - N Xu et al., 2016 CVPR 8 | * positive and negative clicks 9 | * FCN + refinement by Graph Cut 10 | 11 | - [Regional Interactive Image Segmentation Networks](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237559) - JH Liew et al., 2017 ICCV 12 | * click based 13 | * global branch + local regional refinement 14 | 15 | - [DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation](https://arxiv.org/pdf/1707.00652.pdf) - G Wang et al., 2017 arXiv 16 | * click/ scribble based 17 | * Geodesic Distance Transformation 18 | * Refine Network 19 | 20 | - [Deep Extreme Cut: From Extreme Points to Object Segmentation](https://arxiv.org/pdf/1711.09081.pdf](https://arxiv.org/pdf/1711.09081.pdf)) - KK Maninis et al., 2018 CVPR 21 | * Four extreme points 22 | * [[Pytorch code]](https://github.com/scaelles/DEXTR-PyTorch/) 23 | 24 | 25 | - [Interactive Image Segmentation with Latent Diversity](http://vladlen.info/papers/interactive-segmentation.pdf) - Z L et al., 2018 CVPR 26 | * Minimizing the number of clicks 27 | * Multi-modality 28 | * Multiple choice learning 29 | - [Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++](https://arxiv.org/pdf/1803.09693.pdf) - D Acuna et al., 2018 CVPR 30 | * [ Polygon-RNN](https://www.cs.toronto.edu/~urtasun/publications/castrejon_etal_cvpr17.pdf) 31 | 32 | ### natural language 33 | 34 | - [Guide Me: Interacting with Deep Networks](https://arxiv.org/pdf/1803.11544.pdf) - C Rupprecht et al., 2018 CVPR 35 | 36 | ## weakly/semi supervised learning 37 | 38 | - [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://link.springer.com/chapter/10.1007/978-3-319-46493-0_42) - A Kolesnikov et al., 2016 ECCV 39 | 40 | - [What’s the Point: Semantic Segmentation with Point Supervision](https://link.springer.com/chapter/10.1007/978-3-319-46478-7_34) - A Bearman et al., 2016 ECCV 41 | 42 | - [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/papers/Khoreva_Simple_Does_It_CVPR_2017_paper.pdf) - A Khoreva et al., 2017 CVPR 43 | 44 | - [Exploiting saliency for object segmentation from image level labels](http://openaccess.thecvf.com/content_cvpr_2017/papers/Oh_Exploiting_Saliency_for_CVPR_2017_paper.pdf) - SH Oh et al., 2017 CVPR 45 | 46 | 47 | ## Graph based approach 48 | 49 | - [Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images](http://bitsearch.blogspot.kr/2014/01/understanding-graph-cuts-for-image.html) - YY Boykov et al., 2001 ICCV 50 | 51 | - [“GrabCut” — Interactive Foreground Extraction using Iterated Graph Cuts](https://cvg.ethz.ch/teaching/cvl/2012/grabcut-siggraph04.pdf) - C Rother et al., 2004 TOG 52 | 53 | - [Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://www.cv-foundation.org/openaccess/content_cvpr_2016/app/S14-03.pdf) - D Lin et al., 2016 CVPR 54 | 55 | 56 | 57 | # Interactive Video Segmentation 58 | 59 | ## Deep learning approach 60 | 61 | ### natural language 62 | - [Video Object Segmentation with Language Referring Expressions](https://arxiv.org/pdf/1803.08006.pdf) - A Khoreva et al., 2018 arXiv 63 | --------------------------------------------------------------------------------