Convolutional neural networks are prevailing in deep learning tasks. However,
they suffer from massive cost issues when working on mobile devices. Network
pruning is an effective method of model compression to handle such problems.
This paper presents a novel structured network pruning method with auxiliary
gating structures which assigns importance marks to blocks in backbone network
as a criterion when pruning. Block-wise pruning is then realized by proposed
voting strategy, which is different from prevailing methods who prune a model
in small granularity like channel-wise. We further develop a three-stage
training scheduling for the proposed architecture incorporating knowledge
distillation for better performance. Our experiments demonstrate that our
method can achieve state-of-the-arts compression performance for the
classification tasks. In addition, our approach can integrate synergistically
with other pruning methods by providing pretrained models, thus achieving a
better performance than the unpruned model with over 93\% FLOPs reduced.

本文介绍一种基于辅助门控机制的结构化网络剪枝方法，通过给主干网中的块分配重要性标记，并提出了一种块级剪枝的投票策略来解决移动设备上使用卷积神经网络时遇到的成本问题。通过知识蒸馏的三阶段训练计划，提高了模型性能，实现了更好的压缩率。实验证明该方法在分类任务中可以取得最先进的压缩性能。此外，通过提供预训练模型，我们的方法可以与其他剪枝方法协同集成，从而实现比未剪枝模型更优异的性能，并减少了超过 93％的浮点运算。

深度卷积神经网络的辅助门控结构自动分块剪枝

Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks

Recent years, human-object interaction (HOI) detection has achieved
impressive advances. However, conventional two-stage methods are usually slow
in inference. On the other hand, existing one-stage methods mainly focus on the
union regions of interactions, which introduce unnecessary visual information
as disturbances to HOI detection. To tackle the problems above, we propose a
novel one-stage HOI detection approach DIRV in this paper, based on a new
concept called interaction region for the HOI problem. Unlike previous methods,
our approach concentrates on the densely sampled interaction regions across
different scales for each human-object pair, so as to capture the subtle visual
features that is most essential to the interaction. Moreover, in order to
compensate for the detection flaws of a single interaction region, we introduce
a novel voting strategy that makes full use of those overlapped interaction
regions in place of conventional Non-Maximal Suppression (NMS). Extensive
experiments on two popular benchmarks: V-COCO and HICO-DET show that our
approach outperforms existing state-of-the-arts by a large margin with the
highest inference speed and lightest network architecture. We achieved 56.1 mAP
on V-COCO without addtional input. Our code is publicly available at:
this https URL

本文提出了一种基于交互区域的单阶段人 - 物交互检测方法，通过密集采样不同尺度下的交互区域捕捉到最关键的视觉特征，并引入了一种新的投票策略来弥补单个交互区域检测偏差，实验证明该方法在多个数据集上均取得了优于现有方法的效果。