Skip to main navigation Skip to search Skip to main content

Contrastive Class-Specific Encoding for Few-Shot Object Detection

  • Dizhong Lin
  • , Ying Fu
  • , Xin Wang
  • , Shu Hu
  • , Bin Zhu
  • , Qi Song
  • , Xi Wu
  • , Siwei Lyu
  • Chengdu University of Information Technology
  • Keya Medical
  • SUNY Buffalo
  • Microsoft USA

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

4 Scopus citations

Abstract

In this paper, we propose a new few-shot object detection (FSOD) framework that introduces a new contrastive branch to extract the class representation of images, which improves the generalization performance of the detection model for novel classes. Additionally, we investigate the effectiveness of both self-supervised and supervised contrastive losses for class-specific encoding in our framework. Experimental results on the benchmark datasets indicate that our proposed method archives the state-of-the-art performance compared with existing FSOD methods.

Original languageEnglish
Title of host publicationICME 2022 - IEEE International Conference on Multimedia and Expo 2022, Proceedings
PublisherIEEE Computer Society
ISBN (Electronic)9781665485630
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Multimedia and Expo, ICME 2022 - Taipei, Taiwan, Province of China
Duration: Jul 18 2022Jul 22 2022

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2022-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2022 IEEE International Conference on Multimedia and Expo, ICME 2022
Country/TerritoryTaiwan, Province of China
CityTaipei
Period07/18/2207/22/22

Keywords

  • class-specific encoding
  • contrastive learning
  • few-shot object detector
  • Object detection

Fingerprint

Dive into the research topics of 'Contrastive Class-Specific Encoding for Few-Shot Object Detection'. Together they form a unique fingerprint.

Cite this