$ $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.
翻译:随着CNN的最近进展,在高分辨率图像的语义分解方面,在精确度和延缓度方面有了特别的改进;然而,在拥挤的场景中,在探测物体、大规模变异、部分隔离和扭曲方面仍然存在挑战,同时仍然保持流动性和延缓性;我们引入了一个快速高效的动态神经网络,即ASBU-Net,用于高分辨率图像的语义分解,以解决这些问题,并且不使用新的层次来方便量化和嵌入的硬件支持;ABU-Net基于一个新的特征提取模块,即人工空间层(ASBL),该模块在计算和记忆方面是有效的;ASBU-Net构成一个用于建立ASBNet的建筑块。由于这个网络不使用任何特殊的层,因此无法轻易实施、量化和部署在FPGA和其他记忆有限的硬件上;我们介绍了资源和准确性交易的实验,并展示了与其他流行模式相比的强劲性能。