Skip to main navigation Skip to search Skip to main content

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

  • École de technologie supérieure

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

46 Citations (Scopus)

Abstract

This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks, PASCAL-5i and COCO-20i. Particularly, for novel classes, the improvement gains range from 7% to 26% (PASCAL-5i) and from 3% to 12% (COCO-20i) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PublisherIEEE Computer Society
Pages11269-11278
Number of pages10
ISBN (Electronic)9798350301298
DOIs
Publication statusPublished - 2023
Event2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada
Duration: 17 Jun 2023 → 24 Jun 2023

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2023-June
ISSN (Print)1063-6919

Conference

Conference2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Country/TerritoryCanada
CityVancouver
Period17/06/23 → 24/06/23

Keywords

  • Transfer
  • continual
  • low-shot
  • meta
  • or long-tail learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'A Strong Baseline for Generalized Few-Shot Semantic Segmentation'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this