Earticle

현재 위치 Home

Human-Machine Interaction Technology (HIT)

Semantic Segmentation and Boundary Refinement via RoI Tanh-warping and Progressive Unfreezing of ResNet-Based Architecture

첫 페이지 보기
  • 발행기관
    국제인공지능학회(구 한국인터넷방송통신학회) 바로가기
  • 간행물
    The International Journal of Advanced Smart Convergence 바로가기
  • 통권
    Volume 14 Number 4 (2025.12)바로가기
  • 페이지
    pp.209-219
  • 저자
    Viktoriia Reznichenko, Hyo Young Shin, Kye Dong Jung, Cheol Young Go
  • 언어
    영어(ENG)
  • URL
    https://www.earticle.net/Article/A481192

※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

원문정보

초록

영어
We designed a multifunctional neural network to jointly perform semantic segmentation and object boundary extraction. Our goal was to enhance boundary precision, especially for thin and complex facial structures. The model is built on a pre-trained ResNet101 backbone and incorporates ASPP and transposed convolutions to handle objects across multiple scales. A parallel branch structure enables simultaneous learning of semantic regions and boundary details. To further improve visual clarity, we introduce an RoI Tanh-warping technique that selectively distorts the background while preserving the natural appearance of the target region. We also apply a progressive layer unfreezing strategy to allow smooth adaptation to new tasks while retaining key pre-trained features. Experimental results confirm that our method delivers superior boundary accuracy, achieving mean F1 scores of 93.40 and 93.42 on the validation and test datasets. These findings demonstrate that the proposed approach provides both quantitative gains and visually coherent segmentation results.

목차

Abstract
1. Introduction
2. Related Works
3. Theoretical background
3.1 Boundary-Aware Semantic Segmentation (BASS)
3.2 Image Transformation: RoI Tanh-Warping
3.3 Progressive Unfreezing process
3.4 Fine-tuning process
4. Results
5. Conclusions
6. Future Work
Acknowledgement
References

저자

  • Viktoriia Reznichenko [ Student, Department of Software Convergence, Namyangju Campus, Kyungbok University, Korea ]
  • Hyo Young Shin [ Professor, Department of Software Convergence, Namyangju Campus, Kyungbok University, Korea ]
  • Kye Dong Jung [ Visiting professor, Department of Software Convergence, Namyangju Campus, Kyungbok University, Korea ]
  • Cheol Young Go [ Adjunct professor, Department of Software Convergence, Namyangju Campus, Kyungbok University, Korea ] Corresponding Author

참고문헌

자료제공 : 네이버학술정보

간행물 정보

발행기관

  • 발행기관명
    국제인공지능학회(구 한국인터넷방송통신학회) [The International Association for Artificial Intelligence]
  • 설립연도
    2000
  • 분야
    공학>전자/정보통신공학
  • 소개
    인터넷방송, 인터넷 TV , 방송 통신 네트워크 및 관련 분야에 대한 국내는 물론 국제적인 학술, 기술의 진흥발전에 공헌하고 지식 정보화 사회에 기여하고자 한다.

간행물

  • 간행물명
    The International Journal of Advanced Smart Convergence
  • 간기
    계간
  • pISSN
    2288-2847
  • eISSN
    2288-2855
  • 수록기간
    2012~2025
  • 십진분류
    KDC 326 DDC 380

이 권호 내 다른 논문 / The International Journal of Advanced Smart Convergence Volume 14 Number 4

    피인용수 : 0(자료제공 : 네이버학술정보)

    함께 이용한 논문 이 논문을 다운로드한 분들이 이용한 다른 논문입니다.

      페이지 저장