This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
papers:grangier-bottou-collobert-2009 [2013/11/24 16:09] leonb created |
papers:grangier-bottou-collobert-2009 [2013/11/24 16:16] (current) leonb [Notes] |
||
---|---|---|---|
Line 1: | Line 1: | ||
===== Deep Convolutional Networks for Scene Parsing ===== | ===== Deep Convolutional Networks for Scene Parsing ===== | ||
+ | // | ||
+ | We propose a deep learning strategy for scene | ||
+ | parsing, i.e. to asssign a class label to each | ||
+ | pixel of an image. We investigate the use | ||
+ | of deep convolutional network for modeling | ||
+ | the complex scene label structures, relying on | ||
+ | a supervised greedy learning strategy. Compared | ||
+ | to standard approaches based on CRFs, our | ||
+ | strategy does not need hand-crafted features, | ||
+ | allows modeling more complex spatial | ||
+ | dependencies and has a lower inference cost. | ||
+ | Experiments over the MSRC benchmark and | ||
+ | the LabelMe dataset show the eectiveness of | ||
+ | our approach | ||
<box 99% orange> | <box 99% orange> | ||
Line 20: | Line 33: | ||
} | } | ||
+ | |||
+ | ===== Notes ===== | ||
+ | |||
+ | * Parsing examples are available at [[http:// | ||
+ | |||
+ | {{ spanishcity.jpg }} |