.png){kind=icon}
返回
Annotation modification for fine-grained visual recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2016.05.089.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Query modification is an intensively studied and widely used technique in information retrieval, for it helps better understand the intention of the users. In this work, we introduce this idea into fine-grained visual recognition, which is important to ambiguous queries in image retrieval task. Unlike most existing works, which incorporate information about object bounding boxes or parts for extracting discriminative local features, we propose a novel approach from a new viewpoint to solve the fine-grained recognition problem, namely annotation modification. The proposed approach fully exploits the inter-class ambiguity (which is generally regarded as noise) to form active sets of annotations for boosting the fine-grained visual recognition. Specifically, it first obtains some most confusing classes of each image through an easy-to-evaluate classifier, and then modify the annotation of each image using the active set of annotations. To handle the modified annotations, a novel ranking based loss function is further designed to learn effective classification models. We evaluate the proposed approach on three popular fine-grained image datasets (i.e., Oxford-IIIT Pets, Flower-102 and CUB200-2011), and the experimental results clearly demonstrate its effectiveness. (C) 2016 Elsevier B.V. All rights reserved.
Keyword:
Query modification
Annotation modification
Fine-grained visual recognition
Active set
Ranking loss
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
Similarity of the product of the Drosophila neurogenic gene big brain to transmembrane channel proteins.png)
Nature
NatureIF0
PREAI
分享收藏Does Additional Physical Education Improve Exam Performance at the End of Compulsory Education? A Secondary Analysis from a Natural Experiment: The CHAMPS-Study DKChildren
OAAI
ChildrenIF0
OAAI分享收藏Large scale image annotation: learning to rank with joint word-image embeddingsMACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏Dynamic Changes in Myofibroblasts Affect the Carcinogenesis and Prognosis of Bladder Cancer Associated With Tumor Microenvironment Remodeling肌成纤维细胞的动态变化与肿瘤微环境重塑对膀胱癌发生及预后的影响OAAI
OAAI分享收藏Physical activity patterns of ethnic children from low socio-economic environments within the UKOAAI
OAAI分享收藏
查看更多内容