# BiDet: An Efficient Binarized Object Detector

arXiv: https://arxiv.org/abs/2003.03961 · HTML: https://mlsanity.com/paper/2003.03961/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2020.

## Built on by (most cited first, 30 of 33)

- [Q-VLM: Post-training Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2410.08119/) (2024)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets](https://mlsanity.com/paper/2208.08084/) (2022)
- [PTQ4SAM: Post-Training Quantization for Segment Anything](https://mlsanity.com/paper/2405.03144/) (2024)
- [Distribution-sensitive Information Retention for Accurate Binary Neural Network](https://mlsanity.com/paper/2109.12338/) (2021)
- [Q-DETR: An Efficient Low-Bit Quantized Detection Transformer](https://mlsanity.com/paper/2304.00253/) (2023)
- [BiBench: Benchmarking and Analyzing Network Binarization](https://mlsanity.com/paper/2301.11233/) (2023)
- [Resilient Binary Neural Network](https://mlsanity.com/paper/2302.00956/) (2023)
- [Recurrent Bilinear Optimization for Binary Neural Networks](https://mlsanity.com/paper/2209.01542/) (2022)
- [IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectors](https://mlsanity.com/paper/2210.03477/) (2022)
- [Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks](https://mlsanity.com/paper/2110.09195/) (2021)
- [Efficient Multitask Dense Predictor via Binarization](https://mlsanity.com/paper/2405.14136/) (2024)
- [POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing](https://mlsanity.com/paper/2111.13386/) (2021)
- [BiFSMN: Binary Neural Network for Keyword Spotting](https://mlsanity.com/paper/2202.06483/) (2022)
- [BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance](https://mlsanity.com/paper/2211.06987/) (2022)
- [Hoyer regularizer is all you need for ultra low-latency spiking neural networks](https://mlsanity.com/paper/2212.10170/) (2022)
- [Towards practical object detection for weed spraying in precision agriculture](https://mlsanity.com/paper/2109.11048/) (2021)
- [Compacting Binary Neural Networks by Sparse Kernel Selection](https://mlsanity.com/paper/2303.14470/) (2023)
- [Representation Disparity-aware Distillation for 3D Object Detection](https://mlsanity.com/paper/2308.10308/) (2023)
- [1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit](https://mlsanity.com/paper/2408.14267/) (2024)
- [Binarizing by Classification: Is soft function really necessary?](https://mlsanity.com/paper/2205.07433/) (2022)
- [Information-Bottleneck Driven Binary Neural Network for Change Detection](https://mlsanity.com/paper/2507.03504/) (2025)
- [Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning](https://mlsanity.com/paper/2110.08851/) (2021)
- [Binary Neural Networks as a general-propose compute paradigm for on-device computer vision](https://mlsanity.com/paper/2202.03716/) (2022)
- [BiVM: Accurate Binarized Neural Network for Efficient Video Matting](https://mlsanity.com/paper/2507.04456/) (2025)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots](https://mlsanity.com/paper/2112.05534/) (2021)
- [DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs](https://mlsanity.com/paper/2306.15390/) (2023)
- [Long-Tailed Recognition on Binary Networks by Calibrating A Pre-trained Model](https://mlsanity.com/paper/2404.00285/) (2024)
- [NAS-BNN: Neural Architecture Search for Binary Neural Networks](https://mlsanity.com/paper/2408.15484/) (2024)

## Abstract (arXiv)

In this paper, we propose a binarized neural network learning method called BiDet for efficient object detection. Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly. On the contrary, our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal, through which the detection precision is enhanced with alleviated false positives. Specifically, we generalize the information bottleneck (IB) principle to object detection, where the amount of information in the high-level feature maps is constrained and the mutual information between the feature maps and object detection is maximized. Meanwhile, we learn sparse object priors so that the posteriors are concentrated on informative detection prediction with false positive elimination. Extensive experiments on the PASCAL VOC and COCO datasets show that our method outperforms the state-of-the-art binary neural networks by a sizable margin.