We present a joint algorithm for object segmentation that integrates both global shape and local edge information in a deep learning framework. The proposed architecture uses convolutional layers to extract image features, followed by a fully connected section to represent shapes specific to a given object class. This preliminary mask is further refined by matching segmentation mask patches to local features. These processing steps facilitate learning the shape priors effectively with a feedforward pass rather than complex inference methods. Furthermore, our novel convolutional refinement stage presents a convincing alternative to Conditional Random Fields, with promising results on multiple datasets.
|Title of host publication||2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|Publication status||Published - 2015 Dec 9|
|Event||IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada|
Duration: 2015 Sep 27 → 2015 Sep 30
|Name||Proceedings - International Conference on Image Processing, ICIP|
|Other||IEEE International Conference on Image Processing, ICIP 2015|
|Period||15/9/27 → 15/9/30|
Bibliographical notePublisher Copyright:
© 2015 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Signal Processing