Attention-based Multi-patch Aggregation for Image Aesthetic Assessment | |
Kekai, Sheng1,2; Weiming, Dong1; Chongyang, Ma3; Xing, Mei3; Feiyue, Huang4; Bao-Gang, Hu1 | |
2018-10 | |
会议日期 | 2018-10-22 2018-10-26 |
会议地点 | Seoul, Republic of Korea |
关键词 | Image Aesthetic Assessment Attention Mechanism Deep Learning |
英文摘要 | Aggregation structures with explicit information, such as image attributes and scene semantics, are effective and popular for intelligent systems for assessing aesthetics of visual data. However, useful information may not be available due to the high cost of manual annotation and expert design. In this paper, we present a novel multi-patch (MP) aggregation method for image aesthetic assessment. Different from state-of-the-art methods, which augment an MP aggregation network with various visual attributes, we train the model in an end-to-end manner with aesthetic labels only (i.e., aesthetically positive or negative). We achieve the goal by resorting to an attention-based mechanism that adaptively adjusts the weight of each patch during the training process to improve learning efficiency. In addition, we propose a set of objectives with three typical attention mechanisms (i.e., average, minimum, and adaptive) and evaluate their effectiveness on the Aesthetic Visual Analysis (AVA) benchmark. Numerical results show that our approach outperforms existing methods by a large margin. We further verify the effectiveness of the proposed attention-based objectives via ablation studies and shed light on the design of aesthetic assessment systems. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23891] |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
通讯作者 | Weiming, Dong |
作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Snap Inc. 4.Tencent |
推荐引用方式 GB/T 7714 | Kekai, Sheng,Weiming, Dong,Chongyang, Ma,et al. Attention-based Multi-patch Aggregation for Image Aesthetic Assessment[C]. 见:. Seoul, Republic of Korea. 2018-10-22 2018-10-26. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论