Direction Concentration Learning: Enhancing Congruency in Machine Learning
Direction Concentration Learning: Enhancing Congruency in Machine Learning
复制标题
DOI：
10.1109/tpami.2019.2963387
复制
发表时间：
2019-12
影响因子：
23.6
通讯作者：
Yan Luo;Yongkang Wong;M. Kankanhalli;Qi Zhao
中科院分区：
文献类型：
--
作者：
Yan Luo;Yongkang Wong;M. Kankanhalli;Qi Zhao
计算机视觉任务中一个众所周知的挑战是图像的视觉多样性，这可能导致所学知识与当前观察显示的视觉内容之间的一致或不一致。在这项工作中，我们首先将概念学习过程中的这种一致性定义为一致性。形式上，给定一个特定的任务和足够大的数据集，一致性问题发生在学习过程中，即训练数据中特定任务的语义是高度变化的。我们提出了一种方向集中学习（DCL）方法来改善学习过程中的一致性，其中一致性的增强会影响收敛路径的迂回性。实验结果表明，所提出的DCL方法可以推广到最先进的模型和优化器，并提高了显著性预测任务、持续学习任务和分类任务的性能。此外，它有助于减轻持续学习任务中的灾难性遗忘问题。该代码可在https://github.com/luoyan407/congruency上公开获得。
One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In this work, we first define such an agreement in a concepts learning process as congruency. Formally, given a particular task and sufficiently large dataset, the congruency issue occurs in the learning process whereby the task-specific semantics in the training data are highly varying. We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous. The experimental results show that the proposed DCL method generalizes to state-of-the-art models and optimizers, as well as improves the performances of saliency prediction task, continual learning task, and classification task. Moreover, it helps mitigate the catastrophic forgetting problem in the continual learning task. The code is publicly available at https://github.com/luoyan407/congruency.