Pith. sign in

REVIEW 1 cited by

Dual sparse training framework: inducing activation map sparsity via Transformed $\ell1$ regularization

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 2405.19652 v1 pith:I54IEBE2 submitted 2024-05-30 cs.CV

classification cs.CV
keywords sparsityactivationdualframeworksparsetrainingell1method
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Although deep convolutional neural networks have achieved rapid development, it is challenging to widely promote and apply these models on low-power devices, due to computational and storage limitations. To address this issue, researchers have proposed techniques such as model compression, activation sparsity induction, and hardware accelerators. This paper presents a method to induce the sparsity of activation maps based on Transformed $\ell1$ regularization, so as to improve the research in the field of activation sparsity induction. Further, the method is innovatively combined with traditional pruning, constituting a dual sparse training framework. Compared to previous methods, Transformed $\ell1$ can achieve higher sparsity and better adapt to different network structures. Experimental results show that the method achieves improvements by more than 20\% in activation map sparsity on most models and corresponding datasets without compromising the accuracy. Specifically, it achieves a 27.52\% improvement for ResNet18 on the ImageNet dataset, and a 44.04\% improvement for LeNet5 on the MNIST dataset. In addition, the dual sparse training framework can greatly reduce the computational load and provide potential for reducing the required storage during runtime. Specifically, the ResNet18 and ResNet50 models obtained by the dual sparse training framework respectively reduce 81.7\% and 84.13\% of multiplicative floating-point operations, while maintaining accuracy and a low pruning rate.

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. PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention

    cs.LG 2026-08 reject novelty 4.0 of 10

    A CNN forecaster with attention regularized toward smooth peaks shows small gains on blazar flare forecasting, but its sparsity term is constant under softmax and its claimed broad accuracy gains are unsupported.

Pith tools