Papers › LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks

LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks

23 Dec 2024arXiv:2412.18027archive 2025-07-28

Evgeny Hershkovitch Neiterman, Gil Ben-Artzi

Training very deep convolutional networks is challenging, requiring significant computational resources and time. Existing acceleration methods often depend on specific architectures or require network modifications. We introduce LayerDropBack (LDB), a simple yet effective method to accelerate training across a wide range of deep networks. LDB introduces randomness only in the backward pass, maintaining the integrity of the forward pass, guaranteeing that the same network is used during both training and inference. LDB can be seamlessly integrated into the training process of any model without altering its architecture, making it suitable for various network topologies. Our extensive experiments across multiple architectures (ViT, Swin Transformer, EfficientNet, DLA) and datasets (CIFAR-100, ImageNet) show significant training time reductions of 16.93\% to 23.97\%, while preserving or even enhancing model accuracy. Code is available at \url{https://github.com/neiterman21/LDB}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

neiterman21/ldb officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetInverted Residual BlockLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPointwise ConvolutionPosition-Wise Feed-Forward LayerRMSPropReLUResidual ConnectionSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStochastic DepthSwin TransformerTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections