提出可自适应缩放的实时语义分割网络，兼顾速度与精度
Golden Cudgel Network for Real-Time Semantic Segmentation
- 训练时用多路径结构，推理时重参数化为单卷积
- 在3个主流数据集上同时超越现有模型的速度和准确率
- 无需依赖外部教师模型，适合部署于资源受限设备
当前实时语义分割模型虽在性能和速度上表现良好，但仍受多路径结构限制，且部分依赖高性能教师模型进行训练。为此，我们提出黄金法杖网络（GCNet），采用垂直多卷积与水平多路径结构进行训练，并在推理时通过重参数化合并为单一卷积，实现训练时自扩张、推理时自收缩，无需外部教师模型即可达到类似效果。实验表明，GCNet在Cityscapes、CamVid和Pascal VOC 2012数据集上均优于现有最优模型，在性能与速度上取得平衡。代码已开源。
原文摘要 · Abstract (English)
Recent real-time semantic segmentation models, whether single-branch or multi-branch, achieve good performance and speed. However, their speed is limited by multi-path blocks, and some depend on high-performance teacher models for training. To overcome these issues, we propose Golden Cudgel Network (GCNet). Specifically, GCNet uses vertical multi-convolutions and horizontal multi-paths for training, which are reparameterized into a single convolution for inference, optimizing both performance and speed. This design allows GCNet to self-enlarge during training and self-contract during inference, effectively becoming a "teacher model" without needing external ones. Experimental results show that GCNet outperforms existing state-of-the-art models in terms of performance and speed on the Cityscapes, CamVid, and Pascal VOC 2012 datasets. The code is available at https://github.com/gyyang23/GCNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。