Adversarially Occluded Samples for Person Re-identification学习笔记
这是我学习ReID系列看的第二篇paper，这是今天做的笔记。 首先翻译一下这篇文章的题目，在行人重检测中使用对抗重叠的目标作为样本，读起来可能比较拗口。简单点说就是模拟生成将普通训练的ReID模型中那些不能正常检测出来的特殊的数据（这就是Adversarially Occluded Samples，博客中称之为错误样本），将这些数据放入模型中进行训练，可以提高模型的accuracy。 再介绍一下
相关文章
- 1. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记
- 2. Pose-guided Visible Part Matching for Occluded Person ReID阅读笔记
- 3. Pose-Guided Feature Alignment for Occluded Person Re-Identification阅读笔记
- 4. person ReID（行人重识别）2018CVPR paper阅读笔记
- 5. 【CVPR2020】：High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Ide
- 6. Person search: Joint Detection and Identification Feature Learning for Person Search笔记
- 7. 【阅读笔记】Adversarially Regularized Autoencoders
- 8. 论文笔记 | Counterfactual Samples Synthesizing for Robust VQA
- 9. 论文阅读《Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification》
- 10. Group Consistent Similarity Learning via Deep CRF for Person Re-Identification学习笔记
- 更多相关文章...
- • 您已经学习了 XML Schema，下一步学习什么呢？ - XML Schema 教程
- • 我们已经学习了 SQL，下一步学习什么呢？ - SQL 教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • Kotlin学习（一）基本语法
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记
- 2. Pose-guided Visible Part Matching for Occluded Person ReID阅读笔记
- 3. Pose-Guided Feature Alignment for Occluded Person Re-Identification阅读笔记
- 4. person ReID（行人重识别）2018CVPR paper阅读笔记
- 5. 【CVPR2020】：High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Ide
- 6. Person search: Joint Detection and Identification Feature Learning for Person Search笔记
- 7. 【阅读笔记】Adversarially Regularized Autoencoders
- 8. 论文笔记 | Counterfactual Samples Synthesizing for Robust VQA
- 9. 论文阅读《Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification》
- 10. Group Consistent Similarity Learning via Deep CRF for Person Re-Identification学习笔记