AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

SAU: Smooth Activation Function Using Convolution with Approximate Identities

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

ECCV 2022 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace ReLU with SAUShuffleNet V2 2.0x · CIFAR-100top-1 accuracy: 67.11 -> 72.23Improved
replace ReLU with SAUShuffleNet V2 1.0x · CIFAR-100top-1 accuracy: 64.57 -> 68.18Improved
replace ReLU with SAUShuffleNet V2 0.5x · CIFAR-100top-1 accuracy: 62.02 -> 64.39Improved
replace ReLU with SAUEfficientNet B0 · CIFAR-10top-1 accuracy: 95.01 -> 96.07Improved
replace ReLU with SAUMobileNet V2 · CIFAR-10top-1 accuracy: 94.07 -> 95.25Improved
replace ReLU with SAUWideResNet 28-10 · Tiny ImageNettop-1 accuracy: 61.61 -> 63.20Improved
replace ReLU with SAUVGG-16 · MNISTaccuracy: 99.05 -> 99.28Improved
replace ReLU with SAUVGG-16 · SVHNaccuracy: 95.09 -> 95.41Improved
replace ReLU with SAUSSD300 VGG-16 · Pascal VOCmAP: 77.2 -> 77.7Improved
replace ReLU with SAUU-Net · CityscapesmIoU: 69.32 -> 71.02Improved
replace ReLU with SAUU-Net · Cityscapespixel accuracy: 79.60 -> 81.11Improved
replace ReLU with SAUTransformer · WMT14 En-De newstest2014BLEU: 26.2 -> 26.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy