What Makes a Patch Distinct?
Ran Margolin, Ayellet Tal and Lihi Zelnik-Manor
Technion Haifa, Israel



What makes an object salient? Most previous work assert that distinctness is the dominating factor. The difference between the various algorithms is in the way they compute distinctness. Some focus on the patterns, others on the colors, and several add high-level cues and priors. We propose a simple, yet powerful, algorithm that integrates these three factors. Our key contribution is a novel and fast approach to compute pattern distinctness. We rely on the inner statistics of the patches in the image for identifying unique patterns. We provide an extensive evaluation and show that our approach outperforms all state-of-the-art methods on the five most commonly-used datasets.


Ran Margolin, Ayellet Tal and Lihi Zelnik-Manor, “What Makes a Patch Distinct?”, CVPR 2013 [pdf]


We evaluated our approach against four state-of-the-art algorithms: RC[1], CNTX[2], CBS[3], and SVO[4]. These were found to be the “top 4” algorithms according to the benchmark of [5].


Detection was evaluated on five well known datasets

  • MSRA: 5,000 images labeled by nine users. Salient objects were marked by a bounding box. [site]
  • ASD: 1000 images from the MSRA dataset, for which a more refined manually-segmented ground-truth was created. [site]
  • SED1: 100 images of a single salient object annotated manually by three users. [site]
  • SED2: 100 images of two salient objects annotated manually by three users. [site]
  • SOD: 300 images taken from the Berkeley Segmentation Dataset for which seven users selected the boundaries of the salient objects. [site]

[1] M.-M. Cheng, G.-X. Zhang, N. J. Mitra, X. Huang, and S.-M. Hu. Global contrast based salient region detection. In CVPR, pages 409–416, 2011.
[2] S. Goferman, L. Zelnik-Manor, and A. Tal. Context-aware saliency detection. In CVPR, pages 2376–2383, 2010.
[3] H. Jiang, J. Wang, Z. Yuan, T. Liu, N. Zheng, and S. Li. Automatic salient object segmentation based on context and shape prior. In BMVC, page 7, 2012.
[4] K.Chang,T.Liu,H.Chen,andS.Lai.Fusing generic objectness and visual saliency for salient object detection. In ICCV, pages 914–921, 2011.
[5] A. Borji, D. Sihite, and L. Itti. Salient object detection: A benchmark. In ECCV, pages 414–429, 2012


Saliency Detection

Saliency detection code (MATLAB) [download] - Tested on Windows 64-bit Matlab 2011a & 2012b.


Evaluation of Saliency detection code (MATLAB) [download]

The code is for academic purposes only. Please cite this paper if you make use of it:

@conference{margoinPatch13, title={What Makes a Patch Distinct?}, author={Margolin, R. and Tal, A. and Zelnik-Manor, L.}, year = {2013}, booktitle = { CVPR}}

In case of any problems please contact us at: margolin (at) tx.technion.ac.il or hovav (at) ee.technion.ac.il