空洞空间弯曲U型网络（ASBU-Net/LogiNet）
Atrous Space Bender U-Net (ASBU-Net/LogiNet)
AI总结：
针对高分辨率图像语义分割在拥挤场景、尺度变化等方面的挑战，提出基于空洞空间弯曲层的ASBU-Net，无特殊层易部署，在资源与准确率权衡上表现优于主流模型。
摘要：
随着卷积神经网络（CNNs）的最新进展，高分辨率图像语义分割在准确率和延迟方面已取得卓越提升。然而，在拥挤场景目标检测、大尺度变化、部分遮挡与形变问题上仍存在挑战，同时还要兼顾模型轻量化与延迟要求。我们提出一种快速高效的卷积神经网络ASBU-Net，用于高分辨率图像语义分割以解决上述问题，且该网络未使用新型层，便于量化及嵌入式硬件支持。ASBU-Net基于全新的特征提取模块——空洞空间弯曲层（atrous space bender layer, ASBL），该模块在计算和内存方面均具高效性。ASB层构成了构建ASBU-Net的基础模块，由于该网络无特殊层，可轻松实现、量化并部署在FPGA及其他内存有限的硬件上。我们开展了资源与准确率权衡的实验，结果表明其性能优于其他主流模型。
英文摘要：
$ $With recent advances in CNNs, exceptional improvements have been made in semantic segmentation of high resolution images in terms of accuracy and latency. However, challenges still remain in detecting objects in crowded scenes, large scale variations, partial occlusion, and distortions, while still maintaining mobility and latency. We introduce a fast and efficient convolutional neural network, ASBU-Net, for semantic segmentation of high resolution images that addresses these problems and uses no novelty layers for ease of quantization and embedded hardware support. ASBU-Net is based on a new feature extraction module, atrous space bender layer (ASBL), which is efficient in terms of computation and memory. The ASB layers form a building block that is used to make ASBNet. Since this network does not use any special layers it can be easily implemented, quantized and deployed on FPGAs and other hardware with limited memory. We present experiments on resource and accuracy trade-offs and show strong performance compared to other popular models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
