首个专为变化检测设计的二值化神经网络，提升精度与特征区分能力。
Information-Bottleneck Driven Binary Neural Network for Change Detection
- 引入信息瓶颈原理，优化编码器保留关键信息并增强特征分离。
- 在街景与遥感数据集上超越现有二值化模型，达到该领域新基准。
- 适合需要低资源部署的变化检测场景，如边缘设备实时分析。
本文提出Binarized Change Detection（BiCD），首个专为变化检测设计的二值化神经网络（BNN）。传统网络二值化方法直接量化权重与激活，在变化检测模型中严重限制了对输入数据的表征能力，难以区分变化与未变化区域，导致检测精度显著低于实值网络。为克服此问题，BiCD增强二值化网络的表征能力与特征可分性。具体地，我们基于信息瓶颈（IB）原则引入辅助目标，引导编码器保留输入的关键信息并提升特征判别力。由于直接计算互信息不可行，我们设计了一个紧凑、可学习的辅助模块作为近似目标，实现重建损失与标准变化检测损失的联合最小化。在街景与遥感数据集上的大量实验表明，BiCD在基于二值化神经网络的变化检测中建立了新基准，达到该领域的最先进性能。
原文摘要 · Abstract (English)
In this paper, we propose Binarized Change Detection (BiCD), the first binary neural network (BNN) designed specifically for change detection. Conventional network binarization approaches, which directly quantize both weights and activations in change detection models, severely limit the network's ability to represent input data and distinguish between changed and unchanged regions. This results in significantly lower detection accuracy compared to real-valued networks. To overcome these challenges, BiCD enhances both the representational power and feature separability of BNNs, improving detection performance. Specifically, we introduce an auxiliary objective based on the Information Bottleneck (IB) principle, guiding the encoder to retain essential input information while promoting better feature discrimination. Since directly computing mutual information under the IB principle is intractable, we design a compact, learnable auxiliary module as an approximation target, leading to a simple yet effective optimization strategy that minimizes both reconstruction loss and standard change detection loss. Extensive experiments on street-view and remote sensing datasets demonstrate that BiCD establishes a new benchmark for BNN-based change detection, achieving state-of-the-art performance in this domain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。