Deep Semantic Structural Constraints for Zero-Shot Learning | |
Li Y(李岩); Jia Z(贾真); Zhang JG(张俊格); Huang KQ(黄凯奇); Tan TN(谭铁牛) | |
2018 | |
会议日期 | 2018.2.2-2018.2.7 |
会议地点 | New Orleans, Louisiana, USA |
英文摘要 | Zero-shot learning aims to classify unseen image categories by learning a visual-semantic embedding space. In most cases, the traditional methods adopt a separated two-step pipeline that extracts image features from pre-trained CNN models. Then the fixed image features are utilized to learn the embedding space. It leads to the lack of specific structural semantic information of image features for zero-shot learning task. In this paper, we propose an end-to-end trainable Deep Semantic Structural Constraints model to address this issue. The proposed model contains the Image Feature Structure constraint and the Semantic Embedding Structure constraint, which aim to learn structure-preserving image features and endue the learned embedding space with stronger generalization ability respectively. With the assistance of semantic structural information, the model gains more auxiliary clues for zero-shot learning. The state-of-the-art performance certifies the effectiveness of our proposed method. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/19687] |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li Y,Jia Z,Zhang JG,et al. Deep Semantic Structural Constraints for Zero-Shot Learning[C]. 见:. New Orleans, Louisiana, USA. 2018.2.2-2018.2.7. |
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