arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.04044cs.CV
收藏

着色作为视觉理解的代理任务

Colorization as a Proxy Task for Visual Understanding

University of Chicago(芝加哥大学);TTI Chicago(芝加哥丰田技术研究所)

Gustav Larsson, Michael Maire, Gregory Shakhnarovich

摘要:

我们研究并改进了自我监督作为ImageNet预训练的替代品,重点是自动着色作为代理任务。自监督训练已经被证明比其他传统的无监督学习方法更有希望利用未标记的数据。我们在此成功的基础上,评估了我们的自监督网络在几种情况下的能力。在VOC分割和分类任务中,我们展示了不使用ImageNet标签进行预训练表示的方法中最先进的结果。此外,我们提出了第一次深入分析的自我监督通过着色,得出的结论是,制定的损失,培训细节和网络架构发挥重要作用,其有效性。通过重新审视ImageNet预训练范例,进一步扩展了这项调查,提出了一些问题,例如:需要多少训练数据?需要多少个标签?微调后功能会有多大变化?我们将这些问题与自我监督联系起来,通过展示着色提供了与各种ImageNet预训练类似的强大监督信号。

英文摘要:

We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methods not using ImageNet labels for pretraining representations. Moreover, we present the first in-depth analysis of self-supervision via colorization, concluding that formulation of the loss, training details and network architecture play important roles in its effectiveness. This investigation is further expanded by revisiting the ImageNet pretraining paradigm, asking questions such as: How much training data is needed? How many labels are needed? How much do features change when fine-tuned? We relate these questions back to self-supervision by showing that colorization provides a similarly powerful supervisory signal as various flavors of ImageNet pretraining.

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。

↑