Abstract
We treat shape co-segmentation as a representation learning problem and introduce BAE-NET, a branched autoencoder network, for the task. The unsupervised BAE-NET is trained with all shapes in an input collection using a shape reconstruction loss, without ground-truth segmentations. Specifically, the network takes an input shape and encodes it using a convolutional neural network, whereas the decoder concatenates the resulting feature code with a point coordinate and outputs a value indicating whether the point is inside/outside the shape. Importantly, the decoder is branched: each branch learns a compact representation for one commonly recurring part of the shape collection, e.g., airplane wings. By complementing the shape reconstruction loss with a label loss, BAE-NET is easily tuned for one-shot learning. We show unsupervised, weakly supervised, and one-shot learning results by BAE-NET, demonstrating that using only a couple of exemplars, our network can generally outperform state-of-the-art supervised methods trained on hundreds of segmented shapes.
Abstract (translated)
我们将形状共分割视为一个表示学习问题，并为该任务引入分支自动编码器网络BAE-NET。无监督BAE-NET在输入集合中使用形状重建损失训练所有形状，无地面真值分段。具体来说，网络采用输入形状并使用卷积神经网络对其进行编码，而解码器将生成的特征代码与点坐标连接起来，并输出一个值，指示点是否在形状内部/外部。重要的是，解码器是分支的：每个分支学习形状集合中一个通常重复出现的部分（例如，飞机机翼）的紧凑表示。通过将形状重建损失与标签损失相辅相成，BAE-NET很容易调整为一次学习。我们通过BAE-NET显示了无监督、弱监督和一次性学习的结果，证明仅使用几个示例，我们的网络通常可以优于在数百个分段形状上训练的最先进的监督方法。
URL
https://arxiv.org/abs/1903.11228
