• Title/Summary/Keyword: Arbitrary-Scale Super-Resolution

Search Result 2, Processing Time 0.019 seconds

Improvement of Mask-RCNN Performance Using Deep-Learning-Based Arbitrary-Scale Super-Resolution Module (딥러닝 기반 임의적 스케일 초해상도 모듈을 이용한 Mask-RCNN 성능 향상)

  • Ahn, Young-Pill;Park, Hyun-Jun
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.3
    • /
    • pp.381-388
    • /
    • 2022
  • In instance segmentation, Mask-RCNN is mostly used as a base model. Increasing the performance of Mask-RCNN is meaningful because it affects the performance of the derived model. Mask-RCNN has a transform module for unifying size of input images. In this paper, to improve the Mask-RCNN, we apply deep-learning-based ASSR to the resizing part in the transform module and inject calculated scale information into the model using IM(Integration Module). The proposed IM improves instance segmentation performance by 2.5 AP higher than Mask-RCNN in the COCO dataset, and in the periment for optimizing the IM location, the best performance was shown when it was located in the 'Top' before FPN and backbone were combined. Therefore, the proposed method can improve the performance of models using Mask-RCNN as a base model.

Fast Content Adaptive Interpolation Algorithm Using One-Dimensional Patch-Based Learning (일차원 패치 학습을 이용한 고속 내용 기반 보간 기법)

  • Kang, Young-Uk;Jeong, Shin-Cheol;Song, Byung-Cheol
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.48 no.1
    • /
    • pp.54-63
    • /
    • 2011
  • This paper proposes a fast learning-based interpolation algorithm to up-scale an input low-resolution image into a high-resolution image. In conventional learning-based super-resolution, a certain relationship between low-resolution and high-resolution images is learned from various training images and a specific high frequency synthesis information is derived. And then, an arbitrary low resolution image can be super-resolved using the high frequency synthesis information. However, such super-resolution algorithms require heavy memory space to store huge synthesis information as well as significant computation due to two-dimensional matching process. In order to mitigate this problem, this paper presents one-dimensional patch-based learning and synthesis. So, we can noticeably reduce memory cost and computational complexity. Simulation results show that the proposed algorithm provides higher PSNR and SSIM of about 0.7dB and 0.01 on average, respectively than conventional bicubic interpolation algorithm.