arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01355cs.CVeess.IV
收藏

学习压缩域中的语义分割

Semantic Segmentation in Learned Compressed Domain

Waseda University(早稻田大学);Waseda Research Institute for Science and Engineering(早稻田大学科学与工程研究院)

Jinming Liu, Heming Sun, Jiro Katto

摘要:

大多数机器视觉任务(例如,语义分割)基于通过图像压缩算法编码和解码的图像(例如,JPEG)。然而,像素域中的这些解码图像引入了失真,并且它们针对人类感知进行了优化,使得机器视觉任务的性能次优。在本文中,我们提出了一种基于压缩域的方法来改善分割任务。i)提出了动态和静态信道选择方法以减少通过编码获得的压缩表示的冗余。ii)探索和分析了两种不同的变换模块,以帮助压缩表示被转换为分割网络中的特征。实验结果表明,与基于压缩域的方法相比,该方法可以节省15.8%的比特率,与基于像素域的方法相比,可以节省83.6%的比特率和44.8%的推理时间。

英文摘要:

Most machine vision tasks (e.g., semantic segmentation) are based on images encoded and decoded by image compression algorithms (e.g., JPEG). However, these decoded images in the pixel domain introduce distortion, and they are optimized for human perception, making the performance of machine vision tasks suboptimal. In this paper, we propose a method based on the compressed domain to improve segmentation tasks. i) A dynamic and a static channel selection method are proposed to reduce the redundancy of compressed representations that are obtained by encoding. ii) Two different transform modules are explored and analyzed to help the compressed representation be transformed as the features in the segmentation network. The experimental results show that we can save up to 15.8\% bitrates compared with a state-of-the-art compressed domain-based work while saving up to about 83.6\% bitrates and 44.8\% inference time compared with the pixel domain-based method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑