论文标题
实例分离来自介入
Instance Separation Emerges from Inpainting
论文作者
论文摘要
经过培训的部分遮挡图像的深度神经网络对图像组成有深刻的理解，甚至显示出可令人信服地从图像中删除对象。在这项工作中，我们研究了如何利用对图像组成的这种隐式知识进行完全自我监督的实例分离。我们提出了一个衡量两个图像区域的独立性的度量，并通过最大化这种独立性，并通过完全自我保护的镶嵌网络和分开对象。我们在两个显微镜图像数据集上评估了我们的方法，并表明它与完全监督的方法达到了类似的分割性能。
Deep neural networks trained to inpaint partially occluded images show a deep understanding of image composition and have even been shown to remove objects from images convincingly. In this work, we investigate how this implicit knowledge of image composition can be leveraged for fully self-supervised instance separation. We propose a measure for the independence of two image regions given a fully self-supervised inpainting network and separate objects by maximizing this independence. We evaluate our method on two microscopy image datasets and show that it reaches similar segmentation performance to fully supervised methods.
