Bags of Local Convolutional Features for Scalable Instance Search

04/15/2016
by   Eva Mohedano, et al.
0

This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an assignment map, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtaining object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.

READ FULL TEXT
research
12/21/2017

Encoding CNN Activations for Writer Recognition

The encoding of local features is an essential part for writer identific...
research
06/22/2016

Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps

Instance retrieval requires one to search for images that contain a part...
research
11/29/2017

Saliency Weighted Convolutional Features for Instance Search

This work explores attention models to weight the contribution of local ...
research
03/03/2017

Context Aware Query Image Representation for Particular Object Retrieval

The current models of image representation based on Convolutional Neural...
research
06/02/2014

Ambiguous Proximity Distribution

Proximity Distribution Kernel is an effective method for bag-of-featues ...
research
05/25/2018

Dynamicity and Durability in Scalable Visual Instance Search

Visual instance search involves retrieving from a collection of images t...
research
05/30/2015

Bag-of-Genres for Video Genre Retrieval

This paper presents a higher level representation for videos aiming at v...

Please sign up or login with your details

Forgot password? Click here to reset