论文标题
Ainnoseg：高音高的全景分割
AinnoSeg: Panoramic Segmentation with High Perfomance
论文作者
论文摘要
全景分割是一个场景，图像分割任务更加困难。随着CNN网络的开发，全景分割任务已经充分开发了。但是，当前的全景分割算法更关注上下文语义语义，但图像的详细信息还不够。此外，他们无法解决包含闭塞对象细分的准确性，几乎没有对象分割的准确性，对象分割中的边界像素等的问题，旨在解决这些问题，本文提出了一些有用的技巧。 （a）通过更改基本分割模型，该模型可以考虑大型对象和图像详细信息的边界像素分类。 （b）修改损耗函数，以便可以考虑图像中多个对象的边界像素。 （c）使用半监督的方法来重新控制训练过程。 （d）使用多尺度培训和推理。所有这些名为Ainnoseg的操作都可以在著名的数据集ADE20K上实现最先进的性能。
Panoramic segmentation is a scene where image segmentation tasks is more difficult. With the development of CNN networks, panoramic segmentation tasks have been sufficiently developed.However, the current panoramic segmentation algorithms are more concerned with context semantics, but the details of image are not processed enough. Moreover, they cannot solve the problems which contains the accuracy of occluded object segmentation,little object segmentation,boundary pixel in object segmentation etc. Aiming to address these issues, this paper presents some useful tricks. (a) By changing the basic segmentation model, the model can take into account the large objects and the boundary pixel classification of image details. (b) Modify the loss function so that it can take into account the boundary pixels of multiple objects in the image. (c) Use a semi-supervised approach to regain control of the training process. (d) Using multi-scale training and reasoning. All these operations named AinnoSeg, AinnoSeg can achieve state-of-art performance on the well-known dataset ADE20K.
