Hadaptive-Net: Efficient Vision Models via Adaptive Cross-Hadamard Synergy
Hadaptive-Net: Efficient Vision Models via Adaptive Cross-Hadamard Synergy
Recent studies have revealed the immense potential of Hadamard product in enhancing network representational capacity and dimensional compression. However, despite its theoretical promise, this technique has not been systematically explored or effectively applied in practice, leaving its full capabilities underdeveloped. In this work, we first analyze and identify the advantages of Hadamard product over standard convolutional operations in cross-channel interaction and channel expansion. Building upon these insights, we propose a computationally efficient module: Adaptive Cross-Hadamard (ACH), which leverages adaptive cross-channel Hadamard products for high-dimensional channel expansion. Furthermore, we introduce Hadaptive-Net (Hadamard Adaptive Network), a lightweight network backbone for visual tasks, which is demonstrated through experiments that it achieves an unprecedented balance between inference speed and accuracy through our proposed module.
Xuyang Zhang、Xi Zhang、Liang Chen、Hao Shi、Qingshan Guo
计算技术、计算机技术
Xuyang Zhang,Xi Zhang,Liang Chen,Hao Shi,Qingshan Guo.Hadaptive-Net: Efficient Vision Models via Adaptive Cross-Hadamard Synergy[EB/OL].(2025-05-28)[2025-06-13].https://arxiv.org/abs/2505.22226.点此复制
评论