.png){kind=icon}
返回
Fine-grained image analysis via progressive feature learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2018.07.100.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Due to large intra-class variation and inter-class ambiguity, fine-grained object recognition has been a challenging task for decades. A good approach should be able to: (1) discover discriminative local details and (2) align and aggregate these local discriminative patch-level features in an effective manner to facilitate object-level classification. Toward this end, we develop a two-stage framework for fine-grained recognition. In our framework, the first stage aims to discover and align local discriminative features, and the second stage aims to aggregate these features to get classification results. In the first stage, we propose two methods to sequentially discover informative regions. In the second stage, we progressively feed these discovered and aligned regions into a recurrent neural network to obtain object-level representation. Extensive experiments are conducted on three fine-grained image benchmarks, and the results verify the effectiveness of our proposed framework. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Fine-grained recognition
Attention model
Neural network
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization用于细粒度图像分类的学习类别特定字典和共享字典
PREAI
分享收藏
查看更多内容