论文标题
在存在复杂纹理的情况下，以对象为中心表示的感应偏见
Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
论文作者
论文摘要
了解哪些归纳偏见可能有助于无监督的自然场景中以对象为中心的表示是具有挑战性的。在本文中，我们系统地研究了使用神经样式转移的数据集上的两个模型的性能，以获取具有复杂纹理的对象，同时仍保留地面真相注释。我们发现，通过使用单个模块重建每个对象的形状和视觉外观，该模型可以学习更多有用的表示形式，并实现更好的对象分离。此外，我们观察到，调整潜在空间尺寸不足以提高分割性能。最后，与分割质量相比，代表性的下游有用性与分割质量的相关性明显更大。
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging. In this paper, we systematically investigate the performance of two models on datasets where neural style transfer was used to obtain objects with complex textures while still retaining ground-truth annotations. We find that by using a single module to reconstruct both the shape and visual appearance of each object, the model learns more useful representations and achieves better object separation. In addition, we observe that adjusting the latent space size is insufficient to improve segmentation performance. Finally, the downstream usefulness of the representations is significantly more strongly correlated with segmentation quality than with reconstruction accuracy.
