计算机科学
人工智能
分割
图像分割
计算机视觉
模式识别(心理学)
自然语言处理
作者
Zilu Guo,Liuyang Bian,Wei Hu,Jingyu Li,Huasheng Ni,Xuan Huang
标识
DOI:10.1109/tcsvt.2024.3509504
摘要
Atrous convolutions are employed as a method to increase the receptive field in semantic segmentation tasks. However, in previous works of semantic segmentation, it was rarely employed in the shallow layers of the model. We revisit the design of atrous convolutions in modern convolutional neural networks (CNNs), and demonstrate that the concept of using large kernels to apply atrous convolutions could be a more powerful paradigm. We propose three guidelines to apply atrous convolutions more efficiently: Do not only use atrous convolutions, Avoiding the “Atrous Disasters”, Appropriate fusion mechanisms make it perfect. Following these guidelines, we propose DSNet, a Dual-Branch CNN architecture, which incorporates atrous convolutions in the shallow layers of the model architecture, as well as pretraining the nearly entire encoder on ImageNet to achieve better performance. To demonstrate the effectiveness of our approach, our models achieve a new state-of-the-art trade-off between accuracy and speed on ADE20K, Cityscapes and BDD datasets. Specifically, DSNet achieves 40.0% mIOU with inference speed of 179.2 FPS on ADE20K, and 80.4% mIOU with speed of 81.9 FPS on Cityscapes. Additionally, we propose a novel multi-scale attention fusion module, MSAF. It demonstrates outstanding performance in classification as well as downstream tasks such as segmentation. Source code and models are available at Github: https://github.com/takaniwa/DSNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI