TY - GEN
T1 - Context driven scene parsing with attention to rare classes
AU - Yang, Jimei
AU - Price, Brian
AU - Cohen, Scott
AU - Yang, Ming Hsuan
N1 - Publisher Copyright:
© 2014 IEEE.
Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 2014/9/24
Y1 - 2014/9/24
N2 - This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching. We focus on rare object classes, which play an important role in achieving richer semantic understanding of visual scenes, compared to common background classes. Towards this end, we make two novel contributions: rare class expansion and semantic context description. First, considering the long-tailed nature of the label distribution, we expand the retrieval set by rare class exemplars and thus achieve more balanced superpixel classification results. Second, we incorporate both global and local semantic context information through a feedback based mechanism to refine image retrieval and superpixel matching. Results on the SIFTflow and LMSun datasets show the superior performance of our algorithm, especially on the rare classes, without sacrificing overall labeling accuracy.
AB - This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching. We focus on rare object classes, which play an important role in achieving richer semantic understanding of visual scenes, compared to common background classes. Towards this end, we make two novel contributions: rare class expansion and semantic context description. First, considering the long-tailed nature of the label distribution, we expand the retrieval set by rare class exemplars and thus achieve more balanced superpixel classification results. Second, we incorporate both global and local semantic context information through a feedback based mechanism to refine image retrieval and superpixel matching. Results on the SIFTflow and LMSun datasets show the superior performance of our algorithm, especially on the rare classes, without sacrificing overall labeling accuracy.
UR - http://www.scopus.com/inward/record.url?scp=84911380286&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84911380286&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.415
DO - 10.1109/CVPR.2014.415
M3 - Conference contribution
AN - SCOPUS:84911380286
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 3294
EP - 3301
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - IEEE Computer Society
T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Y2 - 23 June 2014 through 28 June 2014
ER -