Papers › Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech...

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

10 Jul 2018ICLR 2019 5arXiv:1807.03848archive 2025-07-28

Chun-Fu Chen, Quanfu Fan, Neil Mallinar, Tom Sercu, Rogerio Feris

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different computational complexity at different branches. Through frequent merging of features from branches at distinct scales, our model obtains multi-scale features while using less computation. The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks,using popular architectures including ResNet and ResNeXt. For object recognition, our approach reduces computation by 33% on object recognition while improving accuracy with 0.9%. Furthermore, our model surpasses state-of-the-art CNN acceleration approaches by a large margin in accuracy and FLOPs reduction. On the task of speech recognition, our proposed multi-scale CNNs save 30% FLOPs with slightly better word error rates, showing good generalization across domains. The codes are available at https://github.com/IBM/BigLittleNet

PaperPDFConference PDFCode

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

Code

IBM/BigLittleNet officialmentioned in paperpytorch report
apoorvagnihotri/big-little-net mentioned on GitHubpytorch report
k0pch4/big-little-net mentioned 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

ObjectObject RecognitionSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Big-Little Module, Big-Little Net

1x1 ConvolutionAverage PoolingBatch NormalizationBig-Little ModuleBig-Little NetBottleneck Residual BlockConvolutionCosine AnnealingDense ConnectionsGlobal Average PoolingGrouped ConvolutionKaiming InitializationLinear LayerMax PoolingNesterov Accelerated GradientRandom Horizontal FlipRandom Resized CropReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionSPEEDSoftmaxWeight Decay

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