Research map / Detection and segmentation / CNN features
Recurrent Bilinear Optimization for Binary Neural Networks
Sheng Xu, Yanjing Li, Tiancheng Wang, Teli Ma, Baochang Zhang, Peng Gao, Yu Qiao, Jinhu Lü, Guodong Guo
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 |
|---|---|---|---|
| use RBONN recurrent bilinear optimization instead of RBNN | 1-bit ResNet-18 · ImageNet (one-stage) | Top-1: 59.6 -> 61.4 | Improved |
| use RBONN instead of ReActNet | 1-bit ResNet-18 · ImageNet (two-stage) | Top-1: 65.9 -> 66.7 | Improved |
| use RBONN instead of ReActNet | ReActNet-A · ImageNet (two-stage) | Top-1: 69.4 -> 70.6 | Improved |
| use RBONN instead of BiDet | 1-bit Faster-RCNN ResNet-18 · PASCAL VOC test2007 | mAP: 59.5 -> 65.4 | Improved |
| use RBONN instead of BiDet | 1-bit SSD VGG-16 · PASCAL VOC test2007 | mAP: 66.0 -> 69.4 | Improved |
| use RBONN instead of BiDet | 1-bit Faster R-CNN ResNet-18 · COCO minival | mAP@[.5,.95]: 15.7 -> 20.6 | Improved |
| use RBONN instead of BiDet | 1-bit SSD VGG-16 · COCO minival | mAP@[.5,.95]: 13.2 -> 17.4 | Improved |
| set backtracking threshold tau to 1 (disable recurrent model) (ablation) | RBONN · ImageNet 1-bit ResNet-18 | Top-1 | Hurt |
| deploy binarized model instead of real-valued | ResNet-18 · ARM Cortex-A55 latency | latency: 1060.2 -> 67.1 | Improved |
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.
- BiDet — BiDet: An Efficient Binarized Object Detector (CVPR 2020) · better on 4 of 4 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
- An Empirical study of Binary Neural Networks' Optimisation (ICLR 2019 · similarity 0.88)
- Resilient Binary Neural Network (AAAI 2023 · similarity 0.88)
- ReCU: Reviving the Dead Weights in Binary Neural Networks (ICCV 2021 · similarity 0.87)
- Associative Recurrent Bilinear Optimization for Domain-Generalized Binary Neural Networks (IJCV 2026 · similarity 0.87)
- Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming (NeurIPS 2024 · similarity 0.86)
- Fast and Slow Gradient Approximation for Binary Neural Network Optimization (AAAI 2025 · similarity 0.85)
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.
