BiSeNet是一种用于实时语义分割的网络，它通过Spatial Path保持原始输入图像的空间大小并编码丰富的空间信息，而Context Path利用轻量级模型和全局平均池化提供大感受野。此外，Attention Refinement Module (ARM) 用于细化每个阶段的特征，以增强高层语义上下文。该网络在保持高精度的同时提高了推理速度。
Research background
•It can be broadly applied to the fields of augmented reality devices, autonomous driving, and video surveillance. These applications have a high demand for efficient inference speed for fast interaction or response.
在现实应用中，图像分割常常需要有效的预测和快速的响应。
Recently, the algorithms of real-time semantic segmentation have shown that there are mainly three approaches to accelerate the model.
•try to restrict the input size to reduce the computation complexity by cropping or resizing.
•prune the channels of the network to boost the inference speed especially in the early stages of the base model.
•
最低0.47元/天 解锁文章
扫一扫
1097
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
