Research map / Architectures and efficiency / Quantization
AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
Zhijun Tu, Xinghao Chen, Pengju Ren, Yunhe Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add AdaBin quantizer to MeliusNet22 (ablation) | MeliusNet22 · ImageNet | Top-1: 63.6 -> 64.6 | Improved |
| add AdaBin to BDenseNet28 (ablation) | BDenseNet28 · ImageNet | Top-1: 62.6 -> 63.7 | Improved |
| add AdaBin to ReActNet-A (ablation) | ReActNet-A · ImageNet | Top-1: 69.4 -> 70.4 | Improved |
| add weight equalization (adaptive weight set) with sign activations (ablation) | BNN ResNet-20 · CIFAR-10 | accuracy: 85.7 -> 86.3 | Improved |
| add gradient-based adaptive activation set (ablation) | BNN ResNet-20 · CIFAR-10 | accuracy: 85.7 -> 87.3 | Improved |
| combine adaptive weight and activation sets (ablation) | BNN ResNet-20 · CIFAR-10 | accuracy: 85.7 -> 87.7 | Improved |
| add Maxout non-linearity instead of PReLU (ablation) | AdaBin ResNet-20 · CIFAR-10 | accuracy: 87.7 -> 88.2 | Improved |
| use KLD-based weight equalization instead of freely learnable weight alpha and beta (ablation) | AdaBin ResNet-20 · CIFAR-10 | accuracy: 86.7 -> 88.2 | Improved |
| add gamma+ scale factor in Maxout (ablation) | AdaBin ResNet-18 · ImageNet | Top-1: 53.2 -> 62.8 | Improved |
| add gamma- scale factor in Maxout (ablation) | AdaBin ResNet-18 · ImageNet | Top-1: 53.2 -> 62.9 | Improved |
| add both gamma- and gamma+ (ablation) | AdaBin ResNet-18 · ImageNet | Top-1: 62.9 -> 63.1 | Improved |
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.
- BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks? (AAAI 2026 · better on 3 of 4 shared results)
- QuEST: Stable Training of LLMs with 1-Bit Weights and Activations (ICML 2025 · better on 2 of 2 shared results)
- OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks (ECCV 2024 · better on 1 of 1 shared result)
- INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold (ICCV 2023 · better on 2 of 2 shared results)
- MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree (ICCV 2023 · better on 1 of 2 shared results)
- BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons (NeurIPS 2022 · better on 1 of 1 shared result)
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.
- ReCU — ReCU: Reviving the Dead Weights in Binary Neural Networks (ICCV 2021) · better on 3 of 3 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
- AdaSTE: An Adaptive Straight-Through Estimator To Train Binary Neural Networks (CVPR 2022 · similarity 0.89)
- Binarized Neural Networks (NeurIPS 2016 · similarity 0.88)
- Towards Accurate Binary Convolutional Neural Network (NeurIPS 2017 · similarity 0.88)
- How to Train a Compact Binary Neural Network with High Accuracy? (AAAI 2017 · similarity 0.88)
- BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks? (AAAI 2026 · similarity 0.88)
- SA-BNN: State-Aware Binary Neural Network (AAAI 2021 · similarity 0.88)
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.
