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 1508.00102cs.CV
收藏

神经网络的失真可预测嵌入

Towards Distortion-Predictable Embedding of Neural Networks

École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Axel Angel

摘要:

当前计算机视觉领域的研究表明,卷积神经网络(CNN)在许多分类任务和计算机视觉问题中具有最先进的性能。CNN的嵌入是最后一层产生的内部表示,可以间接学习拓扑和关系属性。此外,通过使用合适的损失函数,CNN模型可以学习对诸如旋转、视角或照明条件等广泛的非线性失真的不变性。在这项工作中,发现了关于CNN嵌入的新见解,并提出了一个新的损失函数,该函数来自对比损失,可以创建具有更多可预测映射的模型,并量化失真。在典型的失真相关方法中,对应于一幅图像的特征与该图像失真的特征之间没有简单的关系。因此,这些方法需要在每个失真下前馈输入,以找到相应的特征表示。我们的贡献使一个步骤的嵌入扭曲的输入的功能是相关的,可以从彼此的失真的强度。

英文摘要:

Current research in Computer Vision has shown that Convolutional Neural Networks (CNN) give state-of-the-art performance in many classification tasks and Computer Vision problems. The embedding of CNN, which is the internal representation produced by the last layer, can indirectly learn topological and relational properties. Moreover, by using a suitable loss function, CNN models can learn invariance to a wide range of non-linear distortions such as rotation, viewpoint angle or lighting condition. In this work, new insights are discovered about CNN embeddings and a new loss function is proposed, derived from the contrastive loss, that creates models with more predicable mappings and also quantifies distortions. In typical distortion-dependent methods, there is no simple relation between the features corresponding to one image and the features of this image distorted. Therefore, these methods require to feed-forward inputs under every distortions in order to find the corresponding features representations. Our contribution makes a step towards embeddings where features of distorted inputs are related and can be derived from each others by the intensity of the distortion.

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。

↑