Skip to main navigation Skip to search Skip to main content

Deep active learning for joint classification & segmentation with weak annotator

  • École de technologie supérieure
  • McGill University

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

25 Citations (Scopus)

Abstract

CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions. These models allow to simultaneously classify images and extract class-dependent saliency maps, without the need for costly pixel-level annotations. However, they typically yield segmentations with high false-positive rates and, therefore, coarse visualisations, more so when processing challenging images, as encountered in histology. To mitigate this issue, we propose an active learning (AL) framework, which progressively integrates pixel-level annotations during training. Given training data with global image-level labels, our deep weakly-supervised learning model jointly performs supervised image-level classification and active learning for segmentation, integrating pixel annotations by an oracle. Unlike standard AL methods that focus on sample selection, we also leverage large numbers of unlabeled images via pseudo-segmentations (i.e., self-learning at the pixel level), and integrate them with the oracle-annotated samples during training. We report extensive experiments over two challenging benchmarks - high-resolution medical images (histology GlaS data for colon cancer) and natural images (CUB-200-2011 for bird species). Our results indicate that, by simply using random sample selection, the proposed approach can significantly outperform state-of the-art CAMs and AL methods, with an identical oracle-supervision budget. Our code is publicly available1.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3337-3346
Number of pages10
ISBN (Electronic)9780738142661
DOIs
Publication statusPublished - Jan 2021
Event2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021 - Virtual, Online, United States
Duration: 5 Jan 2021 → 9 Jan 2021

Publication series

NameProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021

Conference

Conference2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
Country/TerritoryUnited States
CityVirtual, Online
Period5/01/21 → 9/01/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 3 - Good Health and Well-being
    SDG 3 Good Health and Well-being

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Deep active learning for joint classification & segmentation with weak annotator'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this