A meaningful learning method for zero-shot semantic segmentation  

作　　者：Xianglong LIU Shihao BAI Shan AN Shuo WANG Wei LIU Xiaowei ZHAO Yuqing MA 

机构地区：[1]State Key Lab of Software Development Environment,Beihang University,Beijing 100191,China [2]JD Health International Inc.,Beijing 100191,China

出　　处：《Science China(Information Sciences)》2023年第11期31-49,共19页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.62206010,62022009)。

摘　　要：Zero-shot semantic segmentation,which is developed to segment unseen categories,has attracted increasing attention due to its strong practicability.Previous approaches usually applied semantic-visual mapping based on seen categories to unseen categories,and thus failed to generate meaningful unseen visual representations and struggled to balance the seen and unseen concepts in the classifier.To overcome the above limitations,we propose a novel meaningful learning method that could be embedded into any generationbased zero-shot semantic segmentation model,borrowing the idea from the educational psychology field.The proposed meaningful learning method refers to the process that the new concepts could be learned by relating to existing comprehensible concepts and harmoniously incorporated into the concept schema.Specifically,we introduce a generator with conjugate conceptual correlation(G3C)which generates meaningful unseen visual information through anchoring into existing concepts.Moreover,simulating the rational thinking mechanism,we introduce a fast-slow concept modulator to alleviate the noisy over-correlation problem introduced by G3C and further construct a comprehensive concept schema.Extensive experiments conducted on three benchmarks demonstrate the superior performance of our method,especially according to the commonlyacknowledged h-m Io U(e.g.,4% improvement on the Pascal-VOC dataset).

关 键 词：meaningful learning zero-shot learning semantic segmentation conjugate conceptual correlation fast-slow conceptual modulator 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]