Pith. sign in

REVIEW

S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

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 1911.07033 v2 pith:CBPOB2EO submitted 2019-11-16 cs.CV cs.LG

S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

classification cs.CV cs.LG
keywords inferencedynamicarchitecturemodelnetworkneuralsearchstatic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on "easy" samples while maintaining the overall model performance. In this paper, we introduce a general framework, S2DNAS, which can transform various static CNN models to support dynamic inference via neural architecture search. To this end, based on a given CNN model, we first generate a CNN architecture space in which each architecture is a multi-stage CNN generated from the given model using some predefined transformations. Then, we propose a reinforcement learning based approach to automatically search for the optimal CNN architecture in the generated space. At last, with the searched multi-stage network, we can perform dynamic inference by adaptively choosing a stage to evaluate for each sample. Unlike previous works that introduce irregular computations or complex controllers in the inference or re-design a CNN model from scratch, our method can generalize to most of the popular CNN architectures and the searched dynamic network can be directly deployed using existing deep learning frameworks in various hardware devices.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.