Top-down networks: A coarse-to-fine reimagination of CNNs

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

10 Downloads (Pure)

Abstract

Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli. On the contrary, CNNs employ a fine-to-coarse processing, moving from local, edge-detecting filters to more global ones extracting abstract representations of the input. In this paper we reverse the feature extraction part of standard bottom-up architectures and turn them upside-down: We propose top-down networks. Our proposed coarse-to-fine pathway, by blurring higher frequency information and restoring it only at later stages, offers a line of defence against adversarial attacks that introduce high frequency noise. Moreover, since we increase image resolution with depth, the high resolution of the feature map in the final convolutional layer contributes to the explainability of the network's decision making process. This favors object-driven decisions over context driven ones, and thus provides better localized class activation maps. This paper offers empirical evidence for the applicability of the top-down resolution processing to various existing architectures on multiple visual tasks.

Original languageEnglish
Title of host publication2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Subtitle of host publicationProceedings
EditorsL. O'Conner
Place of PublicationPiscataway
PublisherIEEE
Pages3244-3253
Number of pages10
ISBN (Electronic)978-1-7281-9360-1
ISBN (Print)978-1-7281-9361-8
DOIs
Publication statusPublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
CountryUnited States
CityVirtual, Online
Period14/06/2019/06/20

Bibliographical note

Accepted author manuscript

Fingerprint

Dive into the research topics of 'Top-down networks: A coarse-to-fine reimagination of CNNs'. Together they form a unique fingerprint.

Cite this