基于深度负相关学习的鲁棒回归
Robust Regression via Deep Negative Correlation Learning
摘要:
非线性回归已被广泛用于许多计算机视觉问题(例如,人群计数、年龄估计、情感计算)。在深度学习的保护伞下,存在两种常见的解决方案:i)将非线性回归转换为鲁棒的损失函数,其可与深度卷积网络联合优化,以及ii)利用深度网络的集成。虽然实现了一些改进的性能,但由于选择单个假设的内在限制,前者可能是缺乏的,而后者通常遭受更大的计算复杂性。为了应对这些问题,我们建议通过有效的“分而治之”的方式进行回归。我们的方法的核心是负相关学习的推广,理论和经验都表明,它适用于非深度回归问题。在没有额外参数的情况下,所提出的方法系统地控制偏差-方差-协方差的权衡,并且通常产生深度回归集合,其中每个基础模型都是“准确的”和“多样化的”。此外,我们表明,在所提出的方法中的每个子问题具有较小的Rademacher复杂性,从而更容易优化。在几个不同的和具有挑战性的任务,包括人群计数,个性分析,年龄估计和图像超分辨率的广泛实验证明了具有挑战性的基线的优越性,以及所提出的方法的多功能性。
英文摘要:
Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning, two common solutions exist i) transforming nonlinear regression to a robust loss function which is jointly optimizable with the deep convolutional network, and ii) utilizing ensemble of deep networks. Although some improved performance is achieved, the former may be lacking due to the intrinsic limitation of choosing a single hypothesis and the latter usually suffers from much larger computational complexity. To cope with those issues, we propose to regress via an efficient "divide and conquer" manner. The core of our approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems. Without extra parameters, the proposed method controls the bias-variance-covariance trade-off systematically and usually yields a deep regression ensemble where each base model is both "accurate" and "diversified". Moreover, we show that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize. Extensive experiments on several diverse and challenging tasks including crowd counting, personality analysis, age estimation, and image super-resolution demonstrate the superiority over challenging baselines as well as the versatility of the proposed method.
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。