论文标题
流量胶囊的无监督部分表示
Unsupervised part representation by Flow Capsules
论文作者
论文摘要
胶囊网络旨在将图像解析为对象，零件和关系的层次结构。在有希望的同时，他们仍然受到无法学习有效的低级零件描述的限制。为了解决这个问题，我们提出了一种学习主要胶囊编码器的方法，这些胶囊编码器可以从单个图像中检测原子零件。在训练过程中，我们利用运动作为零件定义的强大感知提示，并在带有遮挡的分层图像模型中使用零件生成的表达解码器。实验证明了在存在多个对象，混乱背景和遮挡的情况下发现了可靠的部分发现。零件解码器会渗透到基础形状面具，有效地填充被检测到的形状的遮挡区域。我们评估了无监督的部分分割和无监督的图像分类的流胶。
Capsule networks aim to parse images into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descriptions. To address this issue we propose a way to learn primary capsule encoders that detect atomic parts from a single image. During training we exploit motion as a powerful perceptual cue for part definition, with an expressive decoder for part generation within a layered image model with occlusion. Experiments demonstrate robust part discovery in the presence of multiple objects, cluttered backgrounds, and occlusion. The part decoder infers the underlying shape masks, effectively filling in occluded regions of the detected shapes. We evaluate FlowCapsules on unsupervised part segmentation and unsupervised image classification.
