Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition
Chu Wang, Marcello Pelillo and Kaleem Siddiqi
Abstract
View based strategies for 3D object recognition have proven to be very successful.
The state-of-the-art methods now achieve over 90% correct category level recognition
performance on appearance images. We improve upon these methods by introducing
a view clustering and pooling layer based on dominant sets. The key idea is to pool
information from views which are similar and thus belong to the same cluster. The pooled
feature vectors are then fed as inputs to the same layer, in a recurrent fashion. This
recurrent clustering and pooling module, when inserted in an off-the-shelf pretrained
CNN, boosts performance for multi-view 3D object recognition, achieving a new state
of the art test set recognition accuracy of 93.8% on the ModelNet 40 database. We
also explore a fast approximate learning strategy for our cluster-pooling CNN, which,
while sacrificing end-to-end learning, greatly improves its training efficiency with only
a slight reduction of recognition accuracy to 93.3%. Our implementation is available at
https://github.com/fate3439/dscnn.
Session
Posters
Files
Paper (PDF)
DOI
10.5244/C.31.64
https://dx.doi.org/10.5244/C.31.64
Citation
Chu Wang, Marcello Pelillo and Kaleem Siddiqi. Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 64.1-64.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_64,
title={Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition},
author={Chu Wang, Marcello Pelillo and Kaleem Siddiqi},
year={2017},
month={September},
pages={64.1-64.12},
articleno={64},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.64},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.64}
}