加速
计算机科学
Softmax函数
人工智能
块(置换群论)
规范化(社会学)
操作员(生物学)
绩效改进
生成模型
机器学习
计算机视觉
生成语法
深度学习
并行计算
生物化学
化学
运营管理
几何学
数学
抑制因子
社会学
人类学
转录因子
经济
基因
作者
Yan Xiong,Zhiqi Li,Yuntao Chen,Rui Wang,Xizhou Zhu,Jiapeng Luo,Wenhai Wang,Tong Lü,Hongsheng Li,Yu Qiao,Lewei Lu,Jie Zhou,Jifeng Dai
出处
期刊:Cornell University - arXiv
日期:2024-01-11
标识
DOI:10.48550/arxiv.2401.06197
摘要
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 increase in processing speed, with DCNv4 achieving more than three times the forward speed. DCNv4 demonstrates exceptional performance across various tasks, including image classification, instance and semantic segmentation, and notably, image generation. When integrated into generative models like U-Net in the latent diffusion model, DCNv4 outperforms its baseline, underscoring its possibility to enhance generative models. In practical applications, replacing DCNv3 with DCNv4 in the InternImage model to create FlashInternImage results in up to 80% speed increase and further performance improvement without further modifications. The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.
科研通智能强力驱动
Strongly Powered by AbleSci AI