TY - GEN
T1 - Nonparametric image parsing using adaptive neighbor sets
AU - Eigen, David
AU - Fergus, Rob
PY - 2012
Y1 - 2012
N2 - This paper proposes a non-parametric approach to scene parsing inspired by the work of Tighe and Lazebnik [22]. In their approach, a simple kNN scheme with multiple descriptor types is used to classify super-pixels. We add two novel mechanisms: (i) a principled and efficient method for learning per-descriptor weights that minimizes classification error, and (ii) a context-driven adaptation of the training set used for each query, which conditions on common classes (which are relatively easy to classify) to improve performance on rare ones. The first technique helps to remove extraneous descriptors that result from the imperfect distance metrics/representations of each super-pixel. The second contribution re-balances the class frequencies, away from the highly-skewed distribution found in real-world scenes. Both methods give a significant performance boost over [22] and the overall system achieves state-of-the-art performance on the SIFT-Flow dataset.
AB - This paper proposes a non-parametric approach to scene parsing inspired by the work of Tighe and Lazebnik [22]. In their approach, a simple kNN scheme with multiple descriptor types is used to classify super-pixels. We add two novel mechanisms: (i) a principled and efficient method for learning per-descriptor weights that minimizes classification error, and (ii) a context-driven adaptation of the training set used for each query, which conditions on common classes (which are relatively easy to classify) to improve performance on rare ones. The first technique helps to remove extraneous descriptors that result from the imperfect distance metrics/representations of each super-pixel. The second contribution re-balances the class frequencies, away from the highly-skewed distribution found in real-world scenes. Both methods give a significant performance boost over [22] and the overall system achieves state-of-the-art performance on the SIFT-Flow dataset.
UR - http://www.scopus.com/inward/record.url?scp=84866674722&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866674722&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6248004
DO - 10.1109/CVPR.2012.6248004
M3 - Conference contribution
AN - SCOPUS:84866674722
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2799
EP - 2806
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -