Papers › CondConv: Conditionally Parameterized Convolutions for Efficient Inference

CondConv: Conditionally Parameterized Convolutions for Efficient Inference

10 Apr 2019NeurIPS 2019 12arXiv:1904.04971archive 2025-07-28

Brandon Yang, Gabriel Bender, Quoc V. Le, Jiquan Ngiam

Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized convolutions (CondConv), which learn specialized convolutional kernels for each example. Replacing normal convolutions with CondConv enables us to increase the size and capacity of a network, while maintaining efficient inference. We demonstrate that scaling networks with CondConv improves the performance and inference cost trade-off of several existing convolutional neural network architectures on both classification and detection tasks. On ImageNet classification, our CondConv approach applied to EfficientNet-B0 achieves state-of-the-art performance of 78.3% accuracy with only 413M multiply-adds. Code and checkpoints for the CondConv Tensorflow layer and CondConv-EfficientNet models are available at: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/condconv.

PaperPDFConference PDFCode

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

Code

tensorflow/tpu officialmentioned in papertfApache-2.0 report
hangg7/deformable-kernels mentioned on GitHubpytorchMIT report
hangg7/deformable-kernels mentioned on GitHubpytorchMIT report
hey-yahei/CondConv.MXNet mentioned on GitHubmxnetMIT report
rwightman/gen-efficientnet-pytorch mentioned on GitHubpytorch report
tensorflow/tpu mentioned on GitHubtf 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

General ClassificationImage ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet EfficientNet-B0 (CondConv) GFLOPs 0.826 #842 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNet-B0 (CondConv) Top 1 Accuracy 78.3% #842 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CondConv

1x1 ConvolutionAutoAugmentAverage PoolingBatch NormalizationBottleneck Residual BlockCondConvConvolutionCosine AnnealingDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetGlobal Average PoolingInverted Residual BlockKaiming InitializationLSTMLinear LayerLinear Warmup With Cosine AnnealingMax PoolingMixupMnasNetMobileNetV1Non Maximum SuppressionPointwise ConvolutionRMSPropReLUResidual BlockResidual ConnectionSSDShake-Shake RegularizationSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockTanh Activation

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