AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Bayesian Optimized 1-Bit CNNs

Jiaxin Gu, Junhe Zhao, Xiaolong Jiang, Baochang Zhang, Jianzhuang Liu, Guodong Guo, Rongrong Ji

ICCV 2019 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 56 citations (OpenAlex)

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
add Bayesian kernel loss (ablation)BONN ResNet18 · ImageNet valtop-1 accuracy (%): 56.3 -> 58.3Improved
add Bayesian feature loss (ablation)BONN ResNet18 · ImageNet valtop-1 accuracy (%): 56.3 -> 58.4Improved
add both Bayesian losses (ablation)BONN ResNet18 · ImageNet valtop-1 accuracy (%): 56.3 -> 59.3Improved
add both Bayesian losses (ablation)BONN ResNet18 · ImageNet valtop-5 accuracy (%): 79.8 -> 81.6Improved
add feature loss on top of kernel loss (ablation)BONN ResNet18 · ImageNet valtop-1 accuracy (%): 58.3 -> 59.3Improved
add kernel loss on top of feature loss (ablation)BONN ResNet18 · ImageNet valtop-1 accuracy (%): 58.4 -> 59.3Improved
replace XNOR-Net with BONNWRN22 16-16-32-64 · CIFAR-10test accuracy (%): 81.90 -> 87.34Improved
replace XNOR-Net with BONNWRN22 16-16-32-64 · CIFAR-100test accuracy (%): 53.17 -> 60.91Improved
replace XNOR-Net with BONNWRN22 64-64-128-256 · CIFAR-10test accuracy (%): 88.52 -> 92.36Improved
replace XNOR-Net with BONNResNet18 · ImageNet valtop-1 accuracy (%): 51.2 -> 59.3Improved
replace Bi-Real Net with BONNResNet18 · ImageNet valtop-1 accuracy (%): 56.4 -> 59.3Improved
replace PCNN with BONNResNet18 · ImageNet valtop-1 accuracy (%): 57.3 -> 59.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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