Affiliations: [a]
Makarov College of Marine Engineering, Jiangsu Ocean University, Lianyungang, China
| [b]
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
| [c]
Department of Data Link and Communication, Nanjing Research Institute of Electronic Engineering, Nanjing, China
Correspondence:
[*]
Corresponding author. Yunyang Yan, Makarov College of Marine Engineering, Jiangsu Ocean University, Lianyungang, 222005, China. E-mail: [email protected].
Abstract: Zero-Shot Learning (ZSL) has made significant progress driven by deep learning and is being promoted further with the advent of generative models. Despite the success of these methods, the type and number of unseen categories are nailed in the generative models, which makes it challenging to recognize unseen categories in an incremental manner, and the profits of some superior performance algorithms largely arise from their advanced capability of feature extraction, such as Transformers. This paper rigidly follows the assumptions introduced in conventional ZSL and proposes a visual feature filtering method based on a semantic mapping model, namely, filtering visual features through class-specific filters to effectively remove class-agnostic information. Extensive experiments are conducted on four benchmark datasets and have achieved very competitive performance.
