PASTS: TOWARD EFFECTIVE DISTILLING TRANSFORMER FOR PANORAMIC SEMANTIC SEGMENTATION

Jihyun Kim, Somi Jeong, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recently, panoramic imaging system has been attracting a lot of attention in various real-world applications due to its all-around sensing abilities. Despite the success of semantic segmentation, the performance of panoramic segmentation is still poor because the number of annotated panoramic datasets is insufficient and existing methods cannot handle the structural distortions in panoramic images caused by wide FoV. In this paper, we present a novel PAnoramic Segmentation Transformers (PASTs) trained by a knowledge distillation strategy with teacher-student branches. We first train the teacher using labeled pinhole images. The knowledge learned from the teacher is transferred to the student via feature distillation. To this end, we exploit the distorted pinhole images to force the attention and the prediction from the teacher consistent with those from the student. In addition, we adopt the entropy loss to train the student with unlabeled panoramic images. Experimental results demonstrate the effectiveness of our method, both qualitatively and quantitatively.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PublisherIEEE Computer Society
Pages2881-2885
Number of pages5
ISBN (Electronic)9781665496209
DOIs
Publication statusPublished - 2022
Event29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
Duration: 2022 Oct 162022 Oct 19

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
Country/TerritoryFrance
CityBordeaux
Period22/10/1622/10/19

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'PASTS: TOWARD EFFECTIVE DISTILLING TRANSFORMER FOR PANORAMIC SEMANTIC SEGMENTATION'. Together they form a unique fingerprint.

Cite this