University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Comparison of mid-level feature coding approaches and pooling strategies in visual concept detection

Koniusz, P, Yan, F and Mikolajczyk, K (2013) Comparison of mid-level feature coding approaches and pooling strategies in visual concept detection Computer Vision and Image Understanding, 117 (5). pp. 479-492.

[img] Text
Restricted to Repository staff only

Download (1MB)


Bag-of-Words lies at a heart of modern object category recognition systems. After descriptors are extracted from images, they are expressed as vectors representing visual word content, referred to as mid-level features. In this paper, we review a number of techniques for generating mid-level features, including two variants of Soft Assignment, Locality-constrained Linear Coding, and Sparse Coding. We also isolate the underlying properties that affect their performance. Moreover, we investigate various pooling methods that aggregate mid-level features into vectors representing images. Average pooling, Max-pooling, and a family of likelihood inspired pooling strategies are scrutinised. We demonstrate how both coding schemes and pooling methods interact with each other. We generalise the investigated pooling methods to account for the descriptor interdependence and introduce an intuitive concept of improved pooling. We also propose a coding-related improvement to increase its speed. Lastly, state-of-the-art performance in classification is demonstrated on Caltech101, Flower17, and ImageCLEF11 datasets. © 2012 Elsevier Inc. All rights reserved.

Item Type: Article
Authors :
Koniusz, P
Yan, F
Mikolajczyk, K
Date : 2013
Identification Number : 10.1016/j.cviu.2012.10.010
Depositing User : Symplectic Elements
Date Deposited : 28 Mar 2017 13:21
Last Modified : 31 Oct 2017 15:12

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800