Pith. sign in

REVIEW 4 cited by

CondenseNet: An Efficient DenseNet using Learned Group Convolutions

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1711.09224 v2 pith:26C2TU2X submitted 2017-11-25 cs.CV

Gao Huang , Shichen Liu , Laurens van der Maaten , Kilian Q. Weinberger This is my paper · ORCID
classification cs.CV
keywords groupconvolutionsefficientlearnedcondensenetconnectivitydensefeature
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented efficiency. It combines dense connectivity with a novel module called learned group convolution. The dense connectivity facilitates feature re-use in the network, whereas learned group convolutions remove connections between layers for which this feature re-use is superfluous. At test time, our model can be implemented using standard group convolutions, allowing for efficient computation in practice. Our experiments show that CondenseNets are far more efficient than state-of-the-art compact convolutional networks such as MobileNets and ShuffleNets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. A Novel Compiler Transformation for Fast Sparse Matrix Multiplication in GPUs

    cs.PL 2025-06 conditional novelty 6.0 of 10

    Enumerate-and-sparse-coarsen, a source-to-source GPU compiler transformation for sparse matrix-dense matrix multiplication, reports 1.4-2.3x speedups over cuBLAS and cuSPARSE on A100 for DLMC matrices, with the exact ...

  2. StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign

    cs.AR 2025-01 conditional novelty 5.0 of 10

    Block-wise structured mixed precision quantizes half of each weight block to low precision with under 1% ImageNet accuracy loss and powers a shifter-based accelerator PE.

  3. Accelerated CNN Training Through Gradient Approximation

    cs.CV 2019-08 conditional novelty 5.0 of 10

    Approximating the weight gradient for a subset of layers and batches yields 3.5% to 7% wall-clock training speedup on CIFAR-10 deep CNNs with minimal validation accuracy loss.

  4. PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block

    cs.CV 2019-09 conditional novelty 4.0 of 10

    Using depthwise convolution to expand channels yields networks with about 60 percent of MobileNetV2's parameters and comparable CIFAR accuracy.

Pith tools