Timezone: »

Hierarchical Granularity Transfer Learning
Shaobo Min · Hongtao Xie · Hantao Yao · Xuran Deng · Zheng-Jun Zha · Yongdong Zhang

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1317

In the real world, object categories usually have a hierarchical granularity tree. Nowadays, most researchers focus on recognizing categories in a specific granularity, \emph{e.g.,} basic-level or sub(ordinate)-level. Compared with basic-level categories, the sub-level categories provide more valuable information, but its training annotations are harder to acquire. Therefore, an attractive problem is how to transfer the knowledge learned from basic-level annotations to sub-level recognition. In this paper, we introduce a new task, named Hierarchical Granularity Transfer Learning (HGTL), to recognize sub-level categories with basic-level annotations and semantic descriptions for hierarchical categories. Different from other recognition tasks, HGTL has a serious granularity gap,~\emph{i.e.,} the two granularities share an image space but have different category domains, which impede the knowledge transfer. To this end, we propose a novel Bi-granularity Semantic Preserving Network (BigSPN) to bridge the granularity gap for robust knowledge transfer. Explicitly, BigSPN constructs specific visual encoders for different granularities, which are aligned with a shared semantic interpreter via a novel subordinate entropy loss. Experiments on three benchmarks with hierarchical granularities show that BigSPN is an effective framework for Hierarchical Granularity Transfer Learning.

Author Information

Shaobo Min (USTC)
Hongtao Xie (University of Science and Technology of China)
Hantao Yao ( Institute of Automation, Chinese Academy of Sciences)
Xuran Deng (University of Science and Technology of China)
Zheng-Jun Zha (University of Science and Technology of China)
Yongdong Zhang (University of Science and Technology of China)

More from the Same Authors