Ask the locals: multi-way local pooling for image recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Ask the locals: multi-way local pooling for image recognition


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.
Fichier principal
Vignette du fichier
boureau-iccv-11.pdf (293.01 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00646816 , version 1 (30-11-2011)


  • HAL Id : hal-00646816 , version 1


Y-Lan Boureau, Nicolas Le Roux, Francis Bach, Jean Ponce, Yann Lecun. Ask the locals: multi-way local pooling for image recognition. ICCV'11 - The 13th International Conference on Computer Vision, Nov 2011, Barcelone, Spain. ⟨hal-00646816⟩
6720 View
1737 Download


Gmail Facebook Twitter LinkedIn More