3 papers
cs.CV2025
Information-Bottleneck Driven Binary Neural Network for Change Detection
Kaijie Yin, Zhiyuan Zhang, Shu Kong +3
In this paper, we propose Binarized Change Detection (BiCD), the first binary neural network (BNN) designed specifically for change detection. Conventional network binarization app…
cs.CV2025
High-Fidelity Differential-information Driven Binary Vision Transformer
Tian Gao, Zhiyuan Zhang, Kaijie Yin +2
The binarization of vision transformers (ViTs) offers a promising approach to addressing the trade-off between high computational/storage demands and the constraints of edge-device…
cs.CV2025
BHViT: Binarized Hybrid Vision Transformer
Tian Gao, Zhiyuan Zhang, Yu Zhang +4
Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN), offering a potential solution to th…