Work

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

Year: 2011
Type: conference-paper
Abstract: Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spa-tially 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 com-mon 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. 1.
Source: HAL
Language: English
Open Access status: green
OpenAlex ID: W4301900913
FWCI:
Cites:
Cited by: 1
Related to: 10