We analyze sequential image labeling methods that sample the posterior label field in order to gather contextual information. We propose an effective method that extracts local Taylor coefficients from the posterior at different scales. Results show that our proposal outperforms state-of-the-art methods on MSRC-21, CAMVID, eTRIMS8 and KAIST2 data sets. © 1979-2012 IEEE.
|Journal||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|Publication status||Published - 1 Jan 2014|
- Contextual modeling
- semantic image labeling
- stacked sequential learning