With deep learning’s success, a limited number of popular deep nets have been widely adopted for various vision tasks. However, this usually results in unnecessarily high complexities and possibly many features of low task utility. In this paper, we address this problem by introducing a task-dependent deep pruning framework based on Fisher’s Linear Discriminant Analysis (LDA). The approach can be applied to convolutional, fully-connected, and module-based deep network structures, in all cases leveraging the high decorrelation of neuron motifs found in the pre-decision space and cross-layer deconv dependency. Moreover, we examine our approach’s potential in network architecture search for specific tasks and analyze the influence of our pruning on model robustness to noises and adversarial attacks. Experimental results on datasets of generic objects (ImageNet, CIFAR100) as well as domain specific tasks (Adience, and LFWA) illustrate our framework’s superior performance over state-of-the-art pruning approaches and fixed compact nets (e.g. SqueezeNet, MobileNet). The proposed method successfully maintains comparable accuracies even after discarding most parameters (98%–99% for VGG16, up to 82% for the already compact InceptionNet) and with significant FLOP reductions (83% for VGG16, up to 64% for InceptionNet). Through pruning, we can also derive smaller, but more accurate and more robust models suitable for the task.

随着深度学习的成功，有限的流行深度网络已被广泛地用于各种视觉任务。然而，这通常导致不必要的高复杂度，并且可能导致任务实用性低的许多特征。在本文中，我们通过引入基于Fisher线性判别分析（LDA）的依赖于任务的深度修剪框架来解决此问题。该方法可以应用于卷积，全连接和基于模块的深度网络结构，在所有情况下都可以利用在预先确定的空间和跨层deconv依赖性中发现的神经元图案的高度去相关性。此外，我们检查了在网络架构中搜索特定任务的方法的潜力，并分析了修剪对噪声和对抗性攻击的模型鲁棒性的影响。通用对象（ImageNet，CIFAR100）以及特定领域任务（Adience和LFWA）的数据集的实验结果表明，我们的框架优于最新的修剪方法和固定的紧凑网络（例如SqueezeNet，MobileNet）。即使丢弃了大多数参数（对于VGG16，98％–99％，对于已经紧凑的InceptionNet，高达82％），并且显着降低了FLOP（对于VGG16，83％，对于InceptionNet，高达64％），所提出的方法仍成功地保持了相当的精度。通过修剪，我们还可以得出更小但更准确和更可靠的适合该任务的模型。即使丢弃了大多数参数（对于VGG16，98％–99％，对于已经紧凑的InceptionNet，高达82％），并且显着降低了FLOP（对于VGG16，83％，对于InceptionNet，高达64％），所提出的方法仍成功地保持了相当的精度。通过修剪，我们还可以得出更小但更准确和更可靠的适合该任务的模型。即使丢弃了大多数参数（对于VGG16，98％–99％，对于已经紧凑的InceptionNet，高达82％），并且显着降低了FLOP（对于VGG16，83％，对于InceptionNet，高达64％），所提出的方法仍成功地保持了相当的精度。通过修剪，我们还可以得出更小但更准确和更可靠的适合该任务的模型。