Zero-annotation object detection with web knowledge transfer

Qingyi Tao, Hao Yang, Jianfei Cai

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. On the contrary, we propose an object detection method that does not require any form of human annotation on target tasks, by exploiting freely available web images. In order to facilitate effective knowledge transfer from web images, we introduce a multi-instance multi-label domain adaption learning framework with two key innovations. First of all, we propose an instance-level adversarial domain adaptation network with attention on foreground objects to transfer the object appearances from web domain to target domain. Second, to preserve the class-specific semantic structure of transferred object features, we propose a simultaneous transfer mechanism to transfer the supervision across domains through pseudo strong label generation. With our end-to-end framework that simultaneously learns a weakly supervised detector and transfers knowledge across domains, we achieved significant improvements over baseline methods on the benchmark datasets.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2018
Subtitle of host publication15th European Conference Munich, Germany, September 8–14, 2018 Proceedings, Part XI
EditorsVittorio Ferrari, Martial Hebert, Cristian Sminchisescu, Yair Weiss
Place of PublicationCham Switzerland
PublisherSpringer
Pages387-403
Number of pages17
ISBN (Electronic)9783030012526
ISBN (Print)9783030012519
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventEuropean Conference on Computer Vision 2018 - Munich, Germany
Duration: 8 Sep 201814 Sep 2018
Conference number: 15th
https://eccv2018.org/
https://link.springer.com/book/10.1007/978-3-030-01246-5 (Proceedings)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11215
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Computer Vision 2018
Abbreviated titleECCV 2018
CountryGermany
CityMunich
Period8/09/1814/09/18
Internet address

Keywords

  • Domain adaptation
  • Object detection
  • Web knowledge transfer

Cite this