Exploring foci of:
arXiv (Cornell University)
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
January 2024 • Yuwen Xiong, Zhiqi Li, Yuntao Chen, Feng Wang, Xizhou Zhu, Jiapeng Luo, Wenhai Wang, Tong Lü, Hongsheng Li, Yu Qiao, Lewei Lu, Jie Zhou, Jifeng Dai
We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1. removing softmax normalization in spatial aggregation to enhance its dynamic property and expressive power and 2. optimizing memory access to minimize redundant operations for speedup. These improvements result in a significantly faster convergence compared to DCNv3 and a substantial i…
Computer Science
Softmax Function
Artificial Intelligence
Machine Learning
Computer Vision
Generative Grammar
Deep Learning
Parallel Computing
Operations Management
Anthropology
Chemistry
Geometry
Mathematics
Biochemistry
Economics