pith. sign in

Aggregated residual transformations for deep neural networks

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 1 cs.LG 1

years

2019 2

verdicts

UNVERDICTED 2

representative citing papers

EPNAS: Efficient Progressive Neural Architecture Search

cs.LG · 2019-07-07 · unverdicted · novelty 5.0

EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.

Slim-CNN: A Light-Weight CNN for Face Attribute Prediction

cs.CV · 2019-07-03 · unverdicted · novelty 3.0

Slim-Net uses stacked Slim Modules of depthwise separable convolutions to predict face attributes on CelebA at 91.24% accuracy with at least 25 times fewer parameters than comparable models.

citing papers explorer

Showing 2 of 2 citing papers.

  • EPNAS: Efficient Progressive Neural Architecture Search cs.LG · 2019-07-07 · unverdicted · none · ref 47

    EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.

  • Slim-CNN: A Light-Weight CNN for Face Attribute Prediction cs.CV · 2019-07-03 · unverdicted · none · ref 19

    Slim-Net uses stacked Slim Modules of depthwise separable convolutions to predict face attributes on CelebA at 91.24% accuracy with at least 25 times fewer parameters than comparable models.