论文信息 - Can Deep Neural Networks Do Image Segmentation by Understanding Insideness?

Can Deep Neural Networks Do Image Segmentation by Understanding Insideness?

THIS MEMO IS REPLACED BY CBMM MEMO 105 https://cbmm.mit.edu/sites/default/files/publications/CBMM-Memo-105.pdf This material is based upon work supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216. CAN DEEP NEURAL NETWORKS DO IMAGE SEGMENTATION BY UNDERSTANDING INSIDENESS? Kimberly M Villalobos, Jamell Dozier, Vilim Štih, Andrew Francl, Frederico Azevedo Tomaso Poggio, Tomotake Sasaki, Xavier Boix Center for Brains, Minds, and Machines

[1] Ohad Shamir,et al. Failures of Gradient-Based Deep Learning , 2017, ICML.

[2] Azriel Rosenfeld,et al. Digital geometry - geometric methods for digital picture analysis , 2004 .

[3] E. Rolls. High-level vision: Object recognition and visual cognition, Shimon Ullman. MIT Press, Bradford (1996), ISBN 0 262 21013 4 , 1997 .

[4] Eric Haines,et al. Point in Polygon Strategies , 1994, Graphics Gems.

[5] S. Ullman. Visual routines , 1984, Cognition.

[6] John R. Harper,et al. Algebraic topology : a first course , 1982 .

[7] Shane Torbert,et al. Applied Computer Science , 2012, Springer New York.

[8] Marvin Minsky,et al. Perceptrons: An Introduction to Computational Geometry , 1969 .