LAV: learning from all vehicles

这篇论文v2版本已经发布，待看
数据集太大暂时无法全部下载，具体的数据集内容查看mdb文件，待看

主要是大概看了一遍代码，跟以往IL-based方法最大的区别就是网络模型复杂，给我的感觉就是从完全end2end，融入了更具体的感知、检测、预测模块，尤其是lidar的处理。
此外，大佬们提及的历史时间信息的使用，后续有待细看。链接

最后贴出自己对模型架构的总结帮助理解，如有误希望大家指出。

后续再对文章内容、代码理解进行更新。

[2022_CVPR_LAV]论文阅读learning from all vehicles相关推荐

[论文阅读] Learning Loss for Active Learning
论文地址:https://arxiv.org/abs/1905.03677 发表于:CVPR'19 Abstract 深度神经网络的性能随着更多的标注数据而提高.问题是用于标注的预算是有限的.解决这个 ...
论文阅读 Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks
Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Graine ...
论文阅读 Learning Transferable Visual Models From Natural Language Supervisio
Learning Transferable Visual Models From Natural Language Supervision Computer Vision and Pattern Re ...
[论文阅读] Learning without Memorizing
论文地址:https://link.springer.com/chapter/10.1007/978-3-319-46493-0_37 代码:https://github.com/stony-hub/ ...
[论文阅读] Learning a Unified Classifier Incrementally via Rebalancing
论文地址:https://openaccess.thecvf.com/content_CVPR_2019/html/Hou_Learning_a_Unified_Classifier_Incremen ...
[论文阅读] Learning Without Forgetting
论文地址:https://link.springer.com/chapter/10.1007/978-3-319-46493-0_37 代码:https://github.com/lizhitwo/L ...
论文阅读-Learning Deep CNN Denoiser Prior for Image Restoration
Zhang K, Zuo W, Gu S, et al. Learning Deep CNN Denoiser Prior for Image Restoration[J]. 2017. 1.引言图 ...
【论文阅读】Learning Traffic as Images: A Deep Convolutional ... [将交通作为图像学习: 用于大规模交通网络速度预测的深度卷积神经网络]（2）
[论文阅读]Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation ...
【论文阅读】Learning Traffic as Images: A Deep Convolutional ... [将交通作为图像学习: 用于大规模交通网络速度预测的深度卷积神经网络]（1）
[论文阅读]Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation ...

[2022_CVPR_LAV]论文阅读learning from all vehicles

LAV: learning from all vehicles

[2022_CVPR_LAV]论文阅读learning from all vehicles相关推荐

最新文章

热门文章