Most of today's popular deep architectures are hand-engineered to be generalists. However, this design procedure usually leads to massive redundant, useless, or even harmful features for specific tasks. Unnecessarily high complexities render deep nets impractical for many real-world applications, especially those without powerful GPU support. In this paper, we attempt to derive task-dependent compact models from a deep discriminant analysis perspective. We propose an iterative and proactive approach for classification tasks which alternates between (1) a pushing step, with an objective to simultaneously maximize class separation, penalize co-variances, and push deep discriminants into alignment with a compact set of neurons, and (2) a pruning step, which discards less useful or even interfering neurons. Deconvolution is adopted to reverse 'unimportant' filters' effects and recover useful contributing sources. A simple network growing strategy based on the basic Inception module is proposed for challenging tasks requiring larger capacity than what the base net can offer. Experiments on the MNIST, CIFAR10, and ImageNet datasets demonstrate our approach's efficacy. On ImageNet, by pushing and pruning our grown Inception-88 model, we achieve more accurate models than Inception nets generated during growing, residual nets, and popular compact nets at similar sizes. We also show that our grown Inception nets (without hard-coded dimension alignment) clearly outperform residual nets of similar complexities.
翻译:当今大多数广受欢迎的深层建筑都是手工设计成通才的。 但是, 这种设计程序通常导致大量多余、无用甚至有害的具体任务。 异常的复杂性使得深网对许多现实世界的应用不切实际, 特别是那些没有强大的GPU支持的应用。 在本文中, 我们试图从深刻的分歧性分析角度出发, 产生依赖任务的契约模型。 我们建议对分类任务采取一种迭接和主动的办法, 将分类任务置于(1) 推一步之间, 目的是同时最大限度地实现阶级分离、 惩罚共变异、 将深刻的分歧与一组神经元的紧凑一致, 和 (2) 快速化步骤, 丢弃了更不那么有用甚至干扰神经元。 在图像网络上, 采用“ 不重要的过滤器” 效果, 并恢复有用的贡献源。 基于基本概念模块的简单网络增长战略, 需要比基本网络所能提供的更强的能力。 对MNIST、 CIFAR10 和图像网络数据集的实验, 显示了我们的方法的功效。 在图像网络上, 将我们的网络的精细化模型, 也显示我们增长的模型 。