arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.05024cs.CV
收藏

通过学习发现伪影的自监督特征学习

Self-Supervised Feature Learning by Learning to Spot Artifacts

University of Bern(伯尔尼大学)

Simon Jenni, Paolo Favaro

摘要:

本文提出了一种基于对抗训练的自监督学习方法。我们的目标是训练一个神经网络来区分真实图像与合成工件的图像,然后从其中间层提取特征,这些特征可以转移到其他数据域和任务。为了生成带有伪影的图像,我们预先训练了一个高容量的自动编码器,然后使用损坏和修复策略:首先,我们冻结自动编码器,并通过随机丢弃其条目来损坏编码器的输出。其次,我们用一个修复网络来增强解码器,并以对抗的方式对解码器进行训练。修复网络通过修复丢弃的特征条目来帮助生成更逼真的图像。为了让机器人专注于工件,我们还让它预测功能中的哪些条目被删除了。我们通过实验证明,通过创建和发现工件学习的功能在几个基准测试中达到了最先进的性能。

英文摘要:

We introduce a novel self-supervised learning method based on adversarial training. Our objective is to train a discriminator network to distinguish real images from images with synthetic artifacts, and then to extract features from its intermediate layers that can be transferred to other data domains and tasks. To generate images with artifacts, we pre-train a high-capacity autoencoder and then we use a damage and repair strategy: First, we freeze the autoencoder and damage the output of the encoder by randomly dropping its entries. Second, we augment the decoder with a repair network, and train it in an adversarial manner against the discriminator. The repair network helps generate more realistic images by inpainting the dropped feature entries. To make the discriminator focus on the artifacts, we also make it predict what entries in the feature were dropped. We demonstrate experimentally that features learned by creating and spotting artifacts achieve state of the art performance in several benchmarks.

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。

↑