Abstract
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end from an input image to a sequence of labeled masks and, compared to methods relying on object proposals, does not require post-processing steps on its output. We study the suitability of our recurrent model on three different instance segmentation benchmarks, namely Pascal VOC 2012, CVPPP Plant Leaf Segmentation and Cityscapes. Further, we analyze the object sorting patterns generated by our model and observe that it learns to follow a consistent pattern, which correlates with the activations learned in the encoder part of our network. Source code and models are available at https://imatge-upc.github.io/rsis/
Abstract (translated)
我们提出了一种语义实例分割的循环模型，它为图像中的每个对象顺序生成二进制掩码及其相关的类概率。我们提出的系统可以从输入图像到标记掩码序列进行端到端的训练，并且与依赖于对象提议的方法相比，不需要对其输出进行后处理步骤。我们研究了我们的重复模型在三种不同的实例分割基准上的适用性，即Pascal VOC 2012，CVPPP Plant Leaf Segmentation和Cityscapes。此外，我们分析了我们的模型生成的对象排序模式，并观察它学会遵循一致的模式，这与我们网络的编码器部分中学习的激活相关。源代码和模型可在https://imatge-upc.github.io/rsis/获得。
URL
https://arxiv.org/abs/1712.00617
