arXiv 1702.086902017-02cs.CVcs.AIcs.LGcs.NEstat.ML

向富人借宝：通过选择性联合微调的深度迁移学习

Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning

Department of Computer Science, The University of Hong Kong（香港大学计算机科学系，香港大学（注：此处严格按要求提取到大学级别，原机构名中“Department of Computer Science”是系，但整体所属机构为The University of Hong Kong，即香港大学））

Weifeng Ge, Yizhou Yu

备注：: To appear in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

深度神经网络在监督学习过程中需要大量标记的训练数据。然而，在许多情况下，收集和标记如此多的数据可能是不可行的。在本文中，我们介绍了一种源-目标选择性联合微调方案，用于在训练数据不足的情况下提高深度学习任务的性能。在该方案中，具有不足的训练数据的目标学习任务与具有丰富的训练数据的另一源学习任务同时执行。然而，源学习任务不使用所有现有的训练数据。我们的核心思想是识别和使用来自原始源学习任务的训练图像的子集，其低级别特征与目标学习任务的特征相似，并联合微调两个任务的共享卷积层。具体来说，我们从两个任务的训练图像上的线性或非线性滤波器组响应计算描述符，并使用这些描述符来搜索源学习任务的训练样本的所需子集。实验表明，我们的选择性联合微调方案在深度学习的训练数据不足的情况下，在多个视觉分类任务上实现了最先进的性能。这些任务包括加州理工学院256，麻省理工学院室内67，牛津花卉102和斯坦福狗120。与不使用源域的微调相比，该方法可以使用单个模型将分类精度提高2% - 10%。

英文摘要：

Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insufficient training data. In this scheme, a target learning task with insufficient training data is carried out simultaneously with another source learning task with abundant training data. However, the source learning task does not use all existing training data. Our core idea is to identify and use a subset of training images from the original source learning task whose low-level characteristics are similar to those from the target learning task, and jointly fine-tune shared convolutional layers for both tasks. Specifically, we compute descriptors from linear or nonlinear filter bank responses on training images from both tasks, and use such descriptors to search for a desired subset of training samples for the source learning task. Experiments demonstrate that our selective joint fine-tuning scheme achieves state-of-the-art performance on multiple visual classification tasks with insufficient training data for deep learning. Such tasks include Caltech 256, MIT Indoor 67, Oxford Flowers 102 and Stanford Dogs 120. In comparison to fine-tuning without a source domain, the proposed method can improve the classification accuracy by 2% - 10% using a single model.

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。