Skip navigation
Skip navigation

In defense of soft-assignment coding

Liu, Lingqiao; Wang, Lei; LIU, Xinwang

Description

In object recognition, soft-assignment coding enjoys computational efficiency and conceptual simplicity. However, its classification performance is inferior to the newly developed sparse or local coding schemes. It would be highly desirable if its classification performance could become comparable to the state-of-the-art, leading to a coding scheme which perfectly combines computational efficiency and classification performance. To achieve this, we revisit soft-assignment coding from two key...[Show more]

dc.contributor.authorLiu, Lingqiao
dc.contributor.authorWang, Lei
dc.contributor.authorLIU, Xinwang
dc.coverage.spatialBarcelona Spain
dc.date.accessioned2015-12-08T22:18:08Z
dc.date.createdNovember 6-13 2011
dc.identifier.isbn9781467300629
dc.identifier.urihttp://hdl.handle.net/1885/31209
dc.description.abstractIn object recognition, soft-assignment coding enjoys computational efficiency and conceptual simplicity. However, its classification performance is inferior to the newly developed sparse or local coding schemes. It would be highly desirable if its classification performance could become comparable to the state-of-the-art, leading to a coding scheme which perfectly combines computational efficiency and classification performance. To achieve this, we revisit soft-assignment coding from two key aspects: classification performance and probabilistic interpretation. For the first aspect, we argue that the inferiority of soft-assignment coding is due to its neglect of the underlying manifold structure of local features. To remedy this, we propose a simple modification to localize the soft-assignment coding, which surprisingly achieves comparable or even better performance than existing sparse or local coding schemes while maintaining its computational advantage. For the second aspect, based on our probabilistic interpretation of the soft-assignment coding, we give a probabilistic explanation to the magic max-pooling operation, which has successfully been used by sparse or local coding schemes but still poorly understood. This probability explanation motivates us to develop a new mix-order max-pooling operation which further improves the classification performance of the proposed coding scheme. As experimentally demonstrated, the localized soft-assignment coding achieves the state-of-the-art classification performance with the highest computational efficiency among the existing coding schemes.
dc.publisherIEEE Computer Society
dc.relation.ispartofseriesIEEE International Conference on Computer Vision (ICCV 2011)
dc.sourceProceedings of IEEE International Conference on Computer Vision (ICCV 2011)
dc.subjectKeywords: Classification performance; Coding scheme; Computational advantages; Conceptual simplicity; Local feature; Probabilistic interpretation; Simple modifications; Computational efficiency; Object recognition; Codes (symbols)
dc.titleIn defense of soft-assignment coding
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2011
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationf5625xPUB81
local.type.statusPublished Version
local.contributor.affiliationLiu, Lingqiao, College of Engineering and Computer Science, ANU
local.contributor.affiliationWang, Lei, College of Engineering and Computer Science, ANU
local.contributor.affiliationLIU, Xinwang, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.startpage2486
local.bibliographicCitation.lastpage2493
local.identifier.doi10.1109/ICCV.2011.6126534
local.identifier.absseo970109 - Expanding Knowledge in Engineering
dc.date.updated2016-02-24T09:39:39Z
local.identifier.scopusID2-s2.0-84863044549
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Liu_In_defense_of_soft-assignment_2011.pdf222.15 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator