Timezone: »
To recognize objects of the unseen classes, most existing Zero-Shot Learning (ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then directly apply it to the target unseen classes. However, in real scenarios, the data distribution between the source and target domain might not match well, thus causing the well-known domain shift problem. Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (\ie alleviate the above domain shift problem). Specifically, three different strategies (symmetric Chamfer-distance,Bipartite matching distance, and Wasserstein distance) are adopted to align the projected unseen semantic centers and visual cluster centers of test instances. We also propose a new training strategy to handle the real cases where many unrelated images exist in the test dataset, which is not considered in previous methods. Experiments on many widely used datasets demonstrate that the proposed visual structure constraint can bring substantial performance gain consistently and achieve state-of-the-art results.
Author Information
Ziyu Wan (City University of Hong Kong)
Dongdong Chen (university of science and technology of china)
Yan Li (Institute of Automation, Chinese Academy of Sciences)
Xingguang Yan (Shenzhen University)
Junge Zhang (CASIA)
Yizhou Yu (Deepwise AI Lab)
Jing Liao (City University of Hong Kong)
More from the Same Authors
-
2022 Poster: Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization »
Chaoqi Chen · Luyao Tang · Feng Liu · Gangming Zhao · Yue Huang · Yizhou Yu -
2023 Poster: CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation »
Chaoqi Chen · Luyao Tang · Yue Huang · Xiaoguang Han · Yizhou Yu -
2022 Spotlight: Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization »
Chaoqi Chen · Luyao Tang · Feng Liu · Gangming Zhao · Yue Huang · Yizhou Yu -
2021 Poster: Stronger NAS with Weaker Predictors »
Junru Wu · Xiyang Dai · Dongdong Chen · Yinpeng Chen · Mengchen Liu · Ye Yu · Zhangyang Wang · Zicheng Liu · Mei Chen · Lu Yuan -
2021 Poster: Coordinated Proximal Policy Optimization »
Zifan Wu · Chao Yu · Deheng Ye · Junge Zhang · haiyin piao · Hankz Hankui Zhuo -
2020 Poster: Passport-aware Normalization for Deep Model Protection »
Jie Zhang · Dongdong Chen · Jing Liao · Weiming Zhang · Gang Hua · Nenghai Yu -
2020 Poster: Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search »
Houwen Peng · Hao Du · Hongyuan Yu · QI LI · Jing Liao · Jianlong Fu