.png){kind=icon}
返回
Curriculum learning of visual attribute clusters for multi-task classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2018.02.028.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped after performing hierarchical clustering based on their correlation. The clusters of tasks are learned in a curriculum learning setup by transferring knowledge between clusters. The learning process within each cluster is performed in a multi-task classification setup. By leveraging the acquired knowledge, we speed-up the process and improve performance. We demonstrate the effectiveness of our method via ablation studies and a detailed analysis of the covariates, on a variety of publicly available datasets of humans standing with their full-body visible. Extensive experimentation has proven that the proposed approach boosts the performance by 4%-10%. (C) 2018 Elsevier Ltd. All rights reserved.
Keyword:
Curriculum learning
Multi-task classification
Visual attributes
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:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏What is the best way for extracting meaningful attributes from pictures?.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mappingPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏
查看更多内容