Particular Object Retrieval With Integral Max-Pooling of CNN Activations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Particular Object Retrieval With Integral Max-Pooling of CNN Activations


Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperform-ing pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN. We build compact feature vectors that encode several image regions without the need to feed multiple inputs to the network. Furthermore, we extend integral images to handle max-pooling on convolutional layer activations, allowing us to efficiently localize matching objects. The resulting bounding box is finally used for image re-ranking. As a result, this paper significantly improves existing CNN-based recognition pipeline: We report for the first time results competing with traditional methods on the challenging Oxford5k and Paris6k datasets.
Fichier principal
Vignette du fichier
1511.05879.pdf (9.46 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01842218 , version 1 (18-07-2018)


  • HAL Id : hal-01842218 , version 1


Giorgos Tolias, Ronan Sicre, Hervé Jégou. Particular Object Retrieval With Integral Max-Pooling of CNN Activations. ICLR 2016 - International Conference on Learning Representations, May 2016, San Juan, Puerto Rico. pp.1-12. ⟨hal-01842218⟩
742 View
868 Download


Gmail Facebook X LinkedIn More