1. SLIC superpixels compared to state-of-the-art superpixel methods  IEEE Trans. Pattern Anal. Mach. Intell., 34 (11) (2012), pp. 2274-2282 【PDF】 【code】标签：Unsupervised methods，Superpixel 

  2. SEEDS: superpixels extracted via energy-driven sampling, in: ECCV, 2012.【PDF】 【code】 【github】标签：Unsupervised methods，Superpixel 

  3. P. Kohli, A. Osokin, S. Jegelka, A principled deep random field model for image segmentation, in: CVPR, 2013.【PDF】 【code】 【作者主页】 标签：Weakly-/semi-supervised methods，Label propagation approaches

  4. H. Zhu, J. Zheng, J. Cai, N. Magnenat-Thalmann Object-level image segmentation using low level cues

    IEEE Trans. Image Process., 22 (10) (2013), pp. 4019-4027 【PDF】 标签：Weakly-/semi-supervised methods，Label propagation approaches

  5. P. Krähenbühl, V. Koltun, Geodesic object proposals, in: ECCV, 2014. 【PDF】 【code】 【作者主页】 【project page】标签：Fully-supervised methods，Object proposals，Class-agnostic object proposals 

  6. P.A. Arbeláez, J. Pont-Tuset, J.T. Barron, F. Marqués, J. Malik, Multiscale combinatorial grouping, in: CVPR, 2014.【PDF】 【project page】标签：Fully-supervised methods，Object proposals，Class-agnostic object proposals 

  7. Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
    TPAMI 2016 【PDF】【project page】标签：Fully-supervised methods，Object proposals，Class-agnostic object proposals 

  8. S. Manen, M. Guillaumin, L.J.V. Gool, Prime object proposals with randomized prim’s algorithm, in: ICCV, 2013.【PDF】  【code】标签：Fully-supervised methods，Object proposals，Class-agnostic object proposals  Generic object detection

  9. J. Tighe, S. Lazebnik, Finding things: image parsing with regions and per-exemplar detectors, in: CVPR, 2013.【PDF】 【project page】 【论文笔记】标签： Fully-supervised methods，Semantic image parsing，Combination of ‘Thing’ and ‘Stuff’ ，Non-parametric approaches

  10. J. Tighe, S. LazebnikSuperparsing – scalable nonparametric image parsing with superpixels

    Int. J. Comput. Vision, 101 (2) (2013), pp. 329-349 【PDF】 【project page】 【论文笔记】标签： Fully-supervised methods，Semantic image parsing，Combination of ‘Thing’ and ‘Stuff’ ，Non-parametric approaches

  11. S. Zheng, M. Cheng, J. Warrell, P. Sturgess, V. Vineet, C. Rother, P.H.S. Torr, Dense semantic image segmentation with objects and attributes, in: CVPR, 2014.【PDF】 【project page】

  12. B. Hariharan, P.A. Arbeláez, R.B. Girshick, J. Malik, Simultaneous detection and segmentation, in: ECCV, 2014.【PDF】 【project page】用了R-CNN

  13. . Dai, K. He, J. Sun,Convolutional feature masking for joint object and stuff segmentation, in: CVPR, 2015.【PDF】【code】

  14. A.C. Müller, S. Behnke Learning depth-sensitive conditional random fields for semantic segmentation of RGB-D images (ICRA) (2014), pp. 6232-6237 【PDF】 标签：Methods using CRF，Plain CRF 

  15. S.H. Khan, M. Bennamoun, F. Sohel, R. TogneriGeometry driven semantic labeling of indoor scenes

    Proceedings of the European Conference on Computer Vision (2014), pp. 679-694【PDF】 标签：Methods using CRF，Higher order CRF

  16. P. Krähenbühl, V. Koltun Efficient inference in fully connected CRFs with gaussian edge potentials

    Proceedings of the Advances in Neural Information Processing Systems(2011), pp. 109-117【PDF】 【project page】 github标签：Contextual models，Inference and energy minimization 

  17. M.P. Kumar, H. Turki, D. Preston, D. Koller Parameter estimation and energy minimization for region-based semantic segmentation

    IEEE Trans. Pattern Anal. Mach. Intell., 37 (7) (2015), pp. 1373-1386 【PDF】 标签：contextual model based scene labeling methods

  18. S. Gould, Zhao J., He X., Zhang Y.Superpixel graph label transfer with learned distance metric

    Proceedings of the European Conference on Computer Vision (2014), pp. 632-647 【PDF】 【project page】标签：Non-parametric methods 

 

 

参考文献：

  1. Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation
  2. Methods and datasets on semantic segmentation: A review