论文标题
学习的压缩域中的语义细分
Semantic Segmentation in Learned Compressed Domain
论文作者
论文摘要
大多数机器视觉任务（例如语义分割）基于图像编码和解码的图像（例如JPEG）。但是，像素域中的这些解码图像会引入失真，并针对人类的感知进行了优化，从而使机器视觉任务的执行次优。在本文中，我们提出了一种基于压缩域的方法，以改善细分任务。 i）提出了一种动态和静态通道选择方法，以减少通过编码获得的压缩表示的冗余。 ii）探索和分析了两个不同的变换模块，以帮助将压缩表示形式转换为分割网络中的特征。实验结果表明，与基于压缩的域的最新作品相比，我们可以节省多达15.8％的比特率，同时与基于像素域的方法相比，节省大约83.6 \％的比特率和44.8％的推理时间。
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.
