Diversity-oriented Contrastive Learning for RGB-T Scene Parsing

Hengyan Liu*, Guangyu Ren, Tianhong Dai, Di Zhang, Pengjing Xu, Wenzhang Zhang, Bintao Hu*

*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

Scene parsing gains improvement under poor lighting conditions by leveraging complementary information from thermal images. However, there are inherent gaps between different modalities and most existing methods propose network modules to reduce the gap. Contrastive learning has gained prominence in the field of computer vision by enabling models to capture rich feature representations through the comparison of positive and negative samples. To extend its applicability to scene parsing, we propose a unique method to enhance the effectiveness of semantic segmentation without negative samples. A determinantal point processes (DPP) based method is proposed to minimize the similarity between relevant image inputs, specifically focusing on learning the intrinsic features between RGB and its thermal images. We further consider the deployment of this task and introduce an efficient vision transformer as a backbone for feature extraction. Our final model achieves a reasonable balance between model size and accuracy.

Original languageEnglish
Title of host publicationProceedings - 2023 2nd International Conference on Sensing, Measurement, Communication and Internet of Things Technologies, SMC-IoT 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages155-160
Number of pages6
ISBN (Electronic)9798350373257
DOIs
Publication statusPublished - 30 May 2024
Event2nd International Conference on Sensing, Measurement, Communication and Internet of Things Technologies, SMC-IoT 2023 - Changsha, China
Duration: 29 Dec 202331 Dec 2023

Publication series

NameInternational Conference on Sensing, Measurement, Communication and Internet of Things Technologies (SMC-IoT)

Conference

Conference2nd International Conference on Sensing, Measurement, Communication and Internet of Things Technologies, SMC-IoT 2023
Country/TerritoryChina
CityChangsha
Period29/12/2331/12/23

Keywords

  • Contrastive Learning
  • Determinantal point processes
  • Scene Parsing

Fingerprint

Dive into the research topics of 'Diversity-oriented Contrastive Learning for RGB-T Scene Parsing'. Together they form a unique fingerprint.

Cite this