超越观察的幻觉：学习用部分观察和不成对的先验知识完成
Hallucinating Beyond Observation: Learning to Complete with Partial Observation and Unpaired Prior Knowledge
摘要：
我们提出了一种新的单步训练策略，允许使用跳过连接的卷积编码器-解码器网络通过幻觉来完成部分观察到的数据。该策略被证明是完成2-D道路布局以及3-D车辆形状的任务。作为输入，它从一个部分观察的领域中获取数据，对于这个领域，没有地面真实数据可用，并且从一个未配对的先验知识领域中获取数据，并以端到端的方式训练网络。我们的单步训练策略与两个最先进的基线进行了比较，一个使用两步自动编码器训练策略，另一个使用对抗策略。我们的新策略在Cityscapes数据集上实现了高达+12.2%的F测量改进。学习后的网络本质上比看不见的数据集上的基线更好地泛化，这一点通过看不见的KITTI数据集上高达+23.8%F测量的改进来证明。此外，我们的方法优于基线使用相同的骨干网络的3-D形状完成基准的利润率为0.006汉明距离。
英文摘要：
We propose a novel single-step training strategy that allows convolutional encoder-decoder networks that use skip connections, to complete partially observed data by means of hallucination. This strategy is demonstrated for the task of completing 2-D road layouts as well as 3-D vehicle shapes. As input, it takes data from a partially observed domain, for which no ground truth is available, and data from an unpaired prior knowledge domain and trains the network in an end-to-end manner. Our single-step training strategy is compared against two state-of-the-art baselines, one using a two-step auto-encoder training strategy and one using an adversarial strategy. Our novel strategy achieves an improvement up to +12.2% F-measure on the Cityscapes dataset. The learned network intrinsically generalizes better than the baselines on unseen datasets, which is demonstrated by an improvement up to +23.8% F-measure on the unseen KITTI dataset. Moreover, our approach outperforms the baselines using the same backbone network on the 3-D shape completion benchmark by a margin of 0.006 Hamming distance.
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。
