AI Paper Atlas

Research map / Architectures and efficiency / Quantization

AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets

Zhijun Tu, Xinghao Chen, Pengju Ren, Yunhe Wang

ECCV 2022 · Architectures and efficiency › Quantization · approach: Binary neural networks · 87 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 AdaBin quantizer to MeliusNet22 (ablation)MeliusNet22 · ImageNetTop-1: 63.6 -> 64.6Improved
add AdaBin to BDenseNet28 (ablation)BDenseNet28 · ImageNetTop-1: 62.6 -> 63.7Improved
add AdaBin to ReActNet-A (ablation)ReActNet-A · ImageNetTop-1: 69.4 -> 70.4Improved
add weight equalization (adaptive weight set) with sign activations (ablation)BNN ResNet-20 · CIFAR-10accuracy: 85.7 -> 86.3Improved
add gradient-based adaptive activation set (ablation)BNN ResNet-20 · CIFAR-10accuracy: 85.7 -> 87.3Improved
combine adaptive weight and activation sets (ablation)BNN ResNet-20 · CIFAR-10accuracy: 85.7 -> 87.7Improved
add Maxout non-linearity instead of PReLU (ablation)AdaBin ResNet-20 · CIFAR-10accuracy: 87.7 -> 88.2Improved
use KLD-based weight equalization instead of freely learnable weight alpha and beta (ablation)AdaBin ResNet-20 · CIFAR-10accuracy: 86.7 -> 88.2Improved
add gamma+ scale factor in Maxout (ablation)AdaBin ResNet-18 · ImageNetTop-1: 53.2 -> 62.8Improved
add gamma- scale factor in Maxout (ablation)AdaBin ResNet-18 · ImageNetTop-1: 53.2 -> 62.9Improved
add both gamma- and gamma+ (ablation)AdaBin ResNet-18 · ImageNetTop-1: 62.9 -> 63.1Improved

Later papers that compared with this method

6 later accepted papers report AdaBin as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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