Pith. sign in

REVIEW 1 cited by

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1906.03951 v1 pith:XEPFBQDW submitted 2019-05-27 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords networksneuralscaninferenceclassifiersdeepdepthframework
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the deployment of deep neural networks on resource-limited edge devices. To address this problem, we propose the so-called SCAN framework for networks training and inference, which is orthogonal and complementary to existing acceleration and compression methods. The proposed SCAN firstly divides neural networks into multiple sections according to their depth and constructs shallow classifiers upon the intermediate features of different sections. Moreover, attention modules and knowledge distillation are utilized to enhance the accuracy of shallow classifiers. Based on this architecture, we further propose a threshold controlled scalable inference mechanism to approach human-like sample-specific inference. Experimental results show that SCAN can be easily equipped on various neural networks without any adjustment on hyper-parameters or neural networks architectures, yielding significant performance gain on CIFAR100 and ImageNet. Codes will be released on github soon.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence

    cs.NI 2019-09 unverdicted novelty 2.0 of 10

    The paper proposes a taxonomy and research roadmap for Edge Intelligence, dividing it into AI for edge and AI on edge, without presenting new empirical results.

Pith tools