Information-Bottleneck Driven Binary Neural Network for Change Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Kaijie, Zhang, Zhiyuan, Kong, Shu, Gao, Tian, Xu, Chengzhong, Kong, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918090920427520
author Yin, Kaijie
Zhang, Zhiyuan
Kong, Shu
Gao, Tian
Xu, Chengzhong
Kong, Hui
author_facet Yin, Kaijie
Zhang, Zhiyuan
Kong, Shu
Gao, Tian
Xu, Chengzhong
Kong, Hui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03504
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Information-Bottleneck Driven Binary Neural Network for Change Detection
Yin, Kaijie
Zhang, Zhiyuan
Kong, Shu
Gao, Tian
Xu, Chengzhong
Kong, Hui
Computer Vision and Pattern Recognition
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.
title Information-Bottleneck Driven Binary Neural Network for Change Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.03504