ICCV2017: Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro
作者：Zhedong Zheng 摘要 提出一个simple的semi-supervised pipline. 该方法只使用训练集而不需要额外的数据。该方法的主要挑战： - （1）如何仅从训练集获取更多的训练数据， - （2）如何使用新产生的数据。 本文提出用generative adversarial network(GAN)产生无标签数据，提出label smoothing regulizat
相关文章
- 1. Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro 论文阅读
- 2. Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification（多伪正则化标签(MpRL)、GAN）
- 3. In Vitro model验证 | Harnessing single-cell genomics to improve the physiological fidelity of organoid
- 4. Generative Adversarial Network (GAN) papers (2018.2.4 更新）
- 5. NVIDIA新作解读：用GAN生成高质量行人图像，辅助行人重识别
- 6. NVIDIA开源DG-Net：用GAN作“淘宝式”换衣，辅助行人重识别
- 7. 【FSR】Feature Space Regularization for Person Re-Identification with One Sample
- 8. 生成对抗网络GAN（四）基于GAN的行人重识别
- 9. 行人重识别(ReID)开源代码
- 10. A Three Player GAN Generating Hard Samples To Improve Classication Networks
- 更多相关文章...
- • SQL IN 操作符 - SQL 教程
- • Swift for-in 循环 - Swift 教程
- • Java 8 Stream 教程
- • JDK13 GA发布：5大特性解读
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. Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro 论文阅读
- 2. Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification（多伪正则化标签(MpRL)、GAN）
- 3. In Vitro model验证 | Harnessing single-cell genomics to improve the physiological fidelity of organoid
- 4. Generative Adversarial Network (GAN) papers (2018.2.4 更新）
- 5. NVIDIA新作解读：用GAN生成高质量行人图像，辅助行人重识别
- 6. NVIDIA开源DG-Net：用GAN作“淘宝式”换衣，辅助行人重识别
- 7. 【FSR】Feature Space Regularization for Person Re-Identification with One Sample
- 8. 生成对抗网络GAN（四）基于GAN的行人重识别
- 9. 行人重识别(ReID)开源代码
- 10. A Three Player GAN Generating Hard Samples To Improve Classication Networks