自监督学习分裂不变等变表示
Self-supervised learning of Split Invariant Equivariant representations
AI总结：
本文提出SIE方法，结合超网络预测器与分裂不变等变表示，在3DIEBench数据集上实现更丰富的自监督表示学习，显著提升等变任务性能。
摘要：
最近在自监督学习方面取得了学习不变或等变表示的进展。虽然不变方法在大规模数据集上进行了评估，但等变方法则在更小、更受控的环境中评估。我们旨在弥合两者之间的差距，以学习适合广泛任务的更多样化表示。我们首先引入一个名为3DIEBench的数据集，该数据集包含来自3D模型的渲染图像，涵盖55个类别和超过250万张图像，其中我们可以完全控制应用于对象的变换。我们进一步引入了一种基于超网络的预测器架构，以学习等变表示，且不会坍缩为不变表示。我们引入了SIE（分裂不变-等变），它将基于超网络的预测器与分成两部分的表示相结合，一部分不变，另一部分等变，以学习更丰富的表示。我们在等变相关任务上，从定性和定量角度都展示了相对于现有方法的显著性能提升。我们进一步分析了我们引入的预测器，并展示了它如何引导学习到的潜在空间。我们希望我们引入的数据集和方法能够在更复杂的场景中无需监督地学习更丰富的表示。代码和数据可在https://github.com/facebookresearch/SIE获取。
英文摘要：
Recent progress has been made towards learning invariant or equivariant representations with self-supervised learning. While invariant methods are evaluated on large scale datasets, equivariant ones are evaluated in smaller, more controlled, settings. We aim at bridging the gap between the two in order to learn more diverse representations that are suitable for a wide range of tasks. We start by introducing a dataset called 3DIEBench, consisting of renderings from 3D models over 55 classes and more than 2.5 million images where we have full control on the transformations applied to the objects. We further introduce a predictor architecture based on hypernetworks to learn equivariant representations with no possible collapse to invariance. We introduce SIE (Split Invariant-Equivariant) which combines the hypernetwork-based predictor with representations split in two parts, one invariant, the other equivariant, to learn richer representations. We demonstrate significant performance gains over existing methods on equivariance related tasks from both a qualitative and quantitative point of view. We further analyze our introduced predictor and show how it steers the learned latent space. We hope that both our introduced dataset and approach will enable learning richer representations without supervision in more complex scenarios. Code and data are available at https://github.com/facebookresearch/SIE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
