[论文阅读] Low-shot Visual Recognition by Shrinking and Hallucinating Features
2017-10-31 18:11
459 查看
arxiv : https://arxiv.org/abs/1606.02819v3
code: https://github.com/facebookresearch/low-shot-shrink-hallucinate
类别样本数很少时候的分类。
使用方法为:
![](http://img.blog.csdn.net/20171031175910514?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvdTAxMTM5NDA1OQ==/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/SouthEast)
实验细节:
对于类别不平衡的处理办法为:
处理方法1不理解。
- we oversample the novel
classes when training the classifier by sampling uniformly
over classes and then uniformly within each chosen class.
- 增加weight decay 来 L2正则化
code: https://github.com/facebookresearch/low-shot-shrink-hallucinate
类别样本数很少时候的分类。
使用方法为:
实验细节:
对于类别不平衡的处理办法为:
处理方法1不理解。
- we oversample the novel
classes when training the classifier by sampling uniformly
over classes and then uniformly within each chosen class.
- 增加weight decay 来 L2正则化
相关文章推荐
- 论文阅读笔记-ClusType: Effective Entity Recognition and Typing by Relation Phrase-Based Clustering
- 【论文阅读笔记】CVPR2015-Long-term Recurrent Convolutional Networks for Visual Recognition and Description
- 论文笔记:Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
- 论文阅读:Segmentation of teeth in CT volumetric dataset by panoramic projection and variational level se
- Fast and Accurate Entity Recognition with Iterated Dilated Convolutions 论文阅读
- 论文阅读:《Neural Machine Translation by Jointly Learning to Align and Translate》
- 【CV论文阅读】+【搬运工】LocNet: Improving Localization Accuracy for Object Detection + A Theoretical analysis of feature pooling in Visual Recognition
- 经典论文阅读——DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations (CVPR 2
- 论文阅读(Lukas Neumann——【ICCV2017】Deep TextSpotter_An End-to-End Trainable Scene Text Localization and Recognition Framework)
- 【论文阅读】Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-S
- 论文阅读理解 - Human Attribute Recognition by Deep Hierarchical Contexts
- 论文阅读:CVPR 2015 FaceNet: A Unified Embedding for Face Recognition and Clustering
- 论文阅读(Lukas Neuman——【ICDAR2015】Efficient Scene Text Localization and Recognition with Local Character Refinement)
- 《2006_ICPR_Low Resolution Character Recognition by Image Quality Evaluation》阅读笔记
- 论文阅读:Learning Visual Question Answering by Bootstrapping Hard Attention
- 论文阅读(Xiang Bai——【TIP2014】A Unified Framework for Multi-Oriented Text Detection and Recognition)
- 论文阅读理解 - Part-based clothing image annotation by visual neighbor retrieval
- 论文阅读理解 - Zero-shot Image Tagging by Hierarchical Semantic Embedding
- 【CV论文阅读】action recognition by dense trajectories
- 论文阅读 | CrystalBall: A Visual Analytic System for Future Event Discovery and Analysis from Social Media Data