arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.03643cs.CV
收藏

计算机视觉的全变分优化层

Total Variation Optimization Layers for Computer Vision

Toyota Technological Institute at Chicago(芝加哥丰田技术研究院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Raymond A. Yeh, Yuan-Ting Hu, Zhongzheng Ren, Alexander G. Schwing

摘要:

深层网络层内的优化已经成为深层网络层设计的新方向。然而,当将这些层应用于计算机视觉任务时,存在两个主要挑战:(a)层内的哪个优化问题有用?; (b)如何确保层内的计算保持高效?为了研究问题(a),在这项工作中,我们提出了全变差(TV)最小化作为计算机视觉的一个层。受图像处理中全变分成功的启发,我们假设TV作为一个层也为深网提供了有用的归纳偏置。我们在五个计算机视觉任务上研究了这一假设:图像分类、弱监督对象定位、边缘保持平滑、边缘检测和图像去噪,并在现有基线上进行了改进。为了实现这些结果,我们必须解决问题(b):我们开发了一种基于GPU的投影牛顿法,它比现有的解决方案快$37\times$。

英文摘要:

Optimization within a layer of a deep-net has emerged as a new direction for deep-net layer design. However, there are two main challenges when applying these layers to computer vision tasks: (a) which optimization problem within a layer is useful?; (b) how to ensure that computation within a layer remains efficient? To study question (a), in this work, we propose total variation (TV) minimization as a layer for computer vision. Motivated by the success of total variation in image processing, we hypothesize that TV as a layer provides useful inductive bias for deep-nets too. We study this hypothesis on five computer vision tasks: image classification, weakly supervised object localization, edge-preserving smoothing, edge detection, and image denoising, improving over existing baselines. To achieve these results we had to address question (b): we developed a GPU-based projected-Newton method which is $37\times$ faster than existing solutions.

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。

↑