Pith. sign in

REVIEW 1 cited by

Mixed Link Networks

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 1802.01808 v1 pith:EAWSU7AO submitted 2018-02-06 cs.LG

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

Basing on the analysis by revealing the equivalence of modern networks, we find that both ResNet and DenseNet are essentially derived from the same "dense topology", yet they only differ in the form of connection -- addition (dubbed "inner link") vs. concatenation (dubbed "outer link"). However, both two forms of connections have the superiority and insufficiency. To combine their advantages and avoid certain limitations on representation learning, we present a highly efficient and modularized Mixed Link Network (MixNet) which is equipped with flexible inner link and outer link modules. Consequently, ResNet, DenseNet and Dual Path Network (DPN) can be regarded as a special case of MixNet, respectively. Furthermore, we demonstrate that MixNets can achieve superior efficiency in parameter over the state-of-the-art architectures on many competitive datasets like CIFAR-10/100, SVHN and ImageNet.

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. Gated Convolutional Networks with Hybrid Connectivity for Image Classification

    cs.CV 2019-08 conditional novelty 5.0 of 10

    HCGNet, a gated hybrid-connectivity network, reports state-of-the-art image-classification accuracy with fewer parameters than prior models, under training recipes that differ from the baselines.

Pith tools