Papers › Channel selection using Gumbel Softmax

Channel selection using Gumbel Softmax

11 Dec 2018ECCV 2020 8arXiv:1812.04180archive 2025-07-28

Charles Herrmann, Richard Strong Bowen, Ramin Zabih

Important applications such as mobile computing require reducing the computational costs of neural network inference. Ideally, applications would specify their preferred tradeoff between accuracy and speed, and the network would optimize this end-to-end, using classification error to remove parts of the network. Increasing speed can be done either during training - e.g., pruning filters - or during inference - e.g., conditionally executing a subset of the layers. We propose a single end-to-end framework that can improve inference efficiency in both settings. We use a combination of batch activation loss and classification loss, and Gumbel reparameterization to learn network structure. We train end-to-end, and the same technique supports pruning as well as conditional computation. We obtain promising experimental results for ImageNet classification with ResNet (45-52% less computation).

PaperPDFConference PDFCode

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

Code

irwinherrmann/stochastic-gates officialmentioned on GitHubpytorch 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.

Tasks

ClassificationGeneral Classificationchannel selection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingGumbel SoftmaxInverted Residual BlockKaiming InitializationMax PoolingPointwise ConvolutionPruningReLUResidual BlockResidual ConnectionSPEED

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