paper-with-me

ESPNet

2000년 도입 · 논문 23편에서 사용

ESPNet is a convolutional neural network for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power.

출처: ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

소개 논문: ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Light-weight neural networks · Computer VisionSemantic Segmentation Models · Computer Vision