VALSE 论文速览 第84期：基于双流对比嵌入网络的组合式零样本学习 ...

论文题目：基于双流对比嵌入网络的组合式零样本学习

作者列表：李翔宇 (西安电子科技大学)、杨旭 (西安电子科技大学)、魏坤 (西安电子科技大学)、邓成 (西安电子科技大学)、杨木李 (西安电子科技大学)

B站观看网址：

https://www.bilibili.com/video/BV1Kv4y1T7SG/

论文摘要：

Compositional Zero-Shot Learning (CZSL)aims to recognize unseen compositions formed from seen state and object during training. Since the same state may be various in the visual appearance while entangled with different objects, CZSL is still a challenging task. Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object compositions, leading to the domain gap between seen and unseen composition sets. In this paper, we propose a novel Siamese Contrastive Embedding Network (SCEN)for unseen composition recognition. Considering the entanglement between state and object, we embed the visual feature into a Siamese Contrastive Space to capture prototypes of them separately, alleviating the interaction between state and object. In addition, we design a State Transition Module (STM)to increase the diversity of training compositions, improving the robustness of the recognition model. Extensive experiments indicate that our method significantly outperforms the state-of-the-art approaches on three challenging benchmark datasets, including the recent proposed C-QGA dataset.

论文信息：

[1] Xiangyu Li, Xu Yang, Kun Wei, Cheng Deng and Muli Yang. Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning. CVPR 2022 (Poster).

论文链接：

[https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Siamese_Contrastive_Embedding_Network_for_Compositional_Zero-Shot_Learning_CVPR_2022_paper.pdf]

代码链接：

[https://github.com/XDUxyLi/SCEN-master]

视频讲者简介：

李翔宇，西安电子科技大学电子工程学院博士研究生，师从邓成教授，主要研究方向是计算机视觉、零样本学习和深度学习，在AAAI、CVPR等会议上发表多篇文章。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：王智慧 (大连理工大学)、杨旭 (西安电子科技大学)

季度责任AC：魏秀参 (南京理工大学)