![](https://img-blog.csdnimg.cn/20201014180756754.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
论文笔记
小珈猫
这个作者很懒,什么都没留下…
展开
-
【论文笔记】Progressive Multi-Granularity Training of Jigsaw Patches(ECCV2020)
代码地址:https://github.com/RuoyiDu/PMG-Progressive-Multi-Granularity-TrainingMotivation:less effort has been placed to which granularities are the most discriminative and how to fuse information cross multi-granularity.关键技术点:(i) a progressive training st原创 2020-11-24 16:26:55 · 855 阅读 · 0 评论 -
【论文笔记】Objects365: A Large-scale, High-quality Dataset for Object Detection(ICCV 2019)
内容:It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community.作为预训练模型有更好的精确率和更快的收敛速度!介绍数据集的标注过程这样更清晰!最大的亮点就是对数据集迁移能力的分析:Iterations所谓iterations就是完成一次epoch所需的batch个数。刚.原创 2020-10-29 14:37:48 · 523 阅读 · 0 评论 -
【论文笔记】IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition
数据集整体概述The IP102 datset contains more than 75,000 images belongs to 102 categories. A natural long-tailed distribution presents on it. In addition, we annotate 19,000 images with bounding boxes for object detection. The IP102 has a hierarchical taxonomy a原创 2020-09-29 18:20:30 · 2628 阅读 · 29 评论 -
【论文笔记】Feature Pyramid Transformer(特征金字塔转换器) (ECCV 2020)
文章目录论文信息一、特征金字塔二、本文论文的内容1.引入库2.读入数据总结论文信息一、特征金字塔在介绍这篇文章前,首先需要了解一下特征金字塔:这篇论文是CVPR2017年的文章,采用特征金字塔代替了传统的Scale handling 方法论文链接:https://arxiv.org/pdf/1612.03144.pdfhttps://blog.csdn.net/xiamentingtao/article/details/78598027https://github.com/kuangli原创 2020-08-17 15:47:51 · 7339 阅读 · 3 评论 -
【论文笔记】Resolution Adaptive Networks for Efficient Inference (CVPR2020)
Resolution Adaptive Networks for Efficient InferenceMotivationMethodExperiments借鉴意义与思考论文地址:http://arxiv.org/abs/2003.07326论文代码:http://github.com/yangle15/RANet-pytorchMotivation深度CNN带来了性能提升的同时也带来了过高的计算量,许多研究放在了如何进行网络加速上面,其中比较直接的是根据样本难易程度进行自动调整的自适应网络。基原创 2020-08-17 11:17:51 · 1488 阅读 · 1 评论 -
【论文笔记】FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding(CVPR2020满分论文)
《FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding》这篇论文来自港中文的林达华团队,是今年CVPR2020的满分论文,特此写博客分析一下。论文地址:https://arxiv.org/abs/2004.06704项目地址:https://sdolivia.github.io/FineGym/...原创 2020-04-26 12:46:43 · 3281 阅读 · 7 评论