Fully Dynamic Inference with Deep Neural Networks [article]

Wenhan Xia, Hongxu Yin, Xiaoliang Dai, Niraj K. Jha
<span title="2020-07-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction. Their cross-domain success, however, is often achieved at the expense of computational cost, high memory bandwidth, and long inference latency, which prevents their deployment in resource-constrained and time-sensitive scenarios, such as edge-side inference and self-driving cars. While recently developed methods for creating efficient deep neural networks
more &raquo; ... are making their real-world deployment more feasible by reducing model size, they do not fully exploit input properties on a per-instance basis to maximize computational efficiency and task accuracy. In particular, most existing methods typically use a one-size-fits-all approach that identically processes all inputs. Motivated by the fact that different images require different feature embeddings to be accurately classified, we propose a fully dynamic paradigm that imparts deep convolutional neural networks with hierarchical inference dynamics at the level of layers and individual convolutional filters/channels. Two compact networks, called Layer-Net (L-Net) and Channel-Net (C-Net), predict on a per-instance basis which layers or filters/channels are redundant and therefore should be skipped. L-Net and C-Net also learn how to scale retained computation outputs to maximize task accuracy. By integrating L-Net and C-Net into a joint design framework, called LC-Net, we consistently outperform state-of-the-art dynamic frameworks with respect to both efficiency and classification accuracy. On the CIFAR-10 dataset, LC-Net results in up to 11.9× fewer floating-point operations (FLOPs) and up to 3.3 inference methods. On the ImageNet dataset, LC-Net achieves up to 1.4× fewer FLOPs and up to 4.6
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.15151v1">arXiv:2007.15151v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i7nlcqqmw5by7pthmgth36ufxm">fatcat:i7nlcqqmw5by7pthmgth36ufxm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828130757/https://arxiv.org/pdf/2007.15151v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/aa/0a/aa0a7e3d14e5d8d654731098b65c828f4d652484.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.15151v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>