Computer Vision, IEEE International Conference on (2011)
Nov. 6, 2011 to Nov. 13, 2011
Y-Lan Boureau , INRIA, France
Nicolas Le Roux , INRIA, France
Francis Bach , INRIA, France
Jean Ponce , Ecole Normale Supérieure, France
Yann LeCun , Courant Institute, New York University, USA
Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spatially local neighborhoods. But pooling is not local in the feature vector space, so that widely dissimilar features may be pooled together if they are in nearby locations. Recent approaches rely on sophisticated encoding methods and more specialized codebooks (or dictionaries), e.g., learned on subsets of descriptors which are close in feature space, to circumvent this problem. In this work, we argue that a common trait found in much recent work in image recognition or retrieval is that it leverages locality in feature space on top of purely spatial locality. We propose to apply this idea in its simplest form to an object recognition system based on the spatial pyramid framework, to increase the performance of small dictionaries with very little added engineering. State-of-the-art results on several object recognition benchmarks show the promise of this approach.
F. Bach, Y. Boureau, Y. LeCun, J. Ponce and N. Le Roux, "Ask the locals: Multi-way local pooling for image recognition," 2011 IEEE International Conference on Computer Vision (ICCV 2011)(ICCV), Barcelona, 2011, pp. 2651-2658.