Towards Accurate BNNs via Modeling Contextual Dependencies

doi:doi:10.57702/m6zk7391

Towards Accurate BNNs via Modeling Contextual Dependencies

The proposed binary model is built on modeling contextual dependencies. An overview of the BCDNet architecture is illustrate in Fig. 4. We first describe the fundamentals of binary MLP block. Then, we introduce the contextual design of binary convolutions with dynamic embeddings. Finally, we present the complete BCDNet architecture with modeling contextual dependencies.

BibTex:

@dataset{Xingrun_Xing_and_Yangguang_Li_and_Wei_Li_and_Wenrui_Ding_and_Yalong_Jiang_and_Yufeng_Wang_and_Jing_Shao_and_Chunlei_Liu_and_Xianglong_Liu_2024,
    abstract = {The proposed binary model is built on modeling contextual dependencies. An overview of the BCDNet architecture is illustrate in Fig. 4. We first describe the fundamentals of binary MLP block. Then, we introduce the contextual design of binary convolutions with dynamic embeddings. Finally, we present the complete BCDNet architecture with modeling contextual dependencies.},
    author = {Xingrun Xing and Yangguang Li and Wei Li and Wenrui Ding and Yalong Jiang and Yufeng Wang and Jing Shao and Chunlei Liu and Xianglong Liu},
    doi = {10.57702/m6zk7391},
    institution = {No Organization},
    keyword = {'binary MLP', 'binary neural networks', 'contextual dependencies'},
    month = {dec},
    publisher = {TIB},
    title = {Towards Accurate BNNs via Modeling Contextual Dependencies},
    url = {https://service.tib.eu/ldmservice/dataset/towards-accurate-bnns-via-modeling-contextual-dependencies},
    year = {2024}
}