We present a learning algorithm for joint object segmentation and categorization that decomposes the original problem into two sub-tasks and admits their bidirectional interaction. In the first stage, in order to decompose output space, we train category-specific segmentation models to generate figure-ground hypotheses. In the second stage, by taking advantage of object figure-ground information, we train a multi-class segment-based categorization model to determine the object class. A re-ranking strategy is then applied to classified segments to obtain the final category-level segmentation results. Experiments on the Graz-02 and Caltech-101 datasets show that the proposed algorithm performs favorably against the state-of-the-art methods.
|Publication status||Published - 2013 Jan 1|
|Event||2013 24th British Machine Vision Conference, BMVC 2013 - Bristol, United Kingdom|
Duration: 2013 Sep 9 → 2013 Sep 13
|Conference||2013 24th British Machine Vision Conference, BMVC 2013|
|Period||13/9/9 → 13/9/13|
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition