按年被提到
20182018 · 1 次2026
视觉、语音与图像生成›卷积网络与图像识别·arXiv:1801.04381 · cs.CV

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2018-01-23 · 最近 2021-10-11
2不同的人
2活跃月份
2讨论串
29,479被引(OpenAlex)
arXiv 摘要(候选层不写导读)

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3. The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on Imagenet classification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as the number of parameters

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论m_ke · 2018-01

“You could try tensorflow object_detection api with tensorflow lite https://github.com/tensorflow/models/tree/master/research/object_detection google also recently put up their mobilenet v2 paper which handles segmentation https://arxiv.org/abs/1801.04381”

Facebook open-sources Detectron原评论 ↗
评论b-3-n · 2021-10

“In contrast to similar works there is no dedicated paper that presents e.g. the neural network or the training procedure. Of course ideas from many papers influenced this work and I can't list them all here. Maybe it helps that the backbone of the network is very similar to MobileNetV2 (https://arxiv.org/abs/1801.04381). Let me know if you have any more q…”

Show HN: YoHa – A practical hand tracking engine原评论 ↗