학술논문
Segmentation Pseudolabel Generation Using the Multiple Instance Learning Choquet Integral
Document Type
Periodical
Author
Source
IEEE Transactions on Fuzzy Systems IEEE Trans. Fuzzy Syst. Fuzzy Systems, IEEE Transactions on. 32(4):1927-1937 Apr, 2024
Subject
Language
ISSN
1063-6706
1941-0034
1941-0034
Abstract
Weakly supervised target detection and semantic segmentation (WSSS) approaches aim at learning object or pixel-level classification labels from imprecise, uncertain, or ambiguous data annotations. A crucial step in WSSS is to produce pseudolabels, which can be used to train a fully supervised semantic classifier. Post hoc attention mechanisms, such as class activation mapping (CAM), are commonly used to produce these pseudolabels. While traditional CAM methods derive feature importance from heuristics on gradient information, this work alternatively investigates whether a subset of discriminative activation feature maps can be down-selected and fused to improve pseudolabel accuracy. More specifically, the multiple instance Choquet integral (MICI) [1] was explored as a method for discriminative feature selection and fusion. Experimental results on both synthetic and real-world datasets indicate the utility of the MICI in down-selecting class-discriminative activation feature maps. Fusion of the MICI-selected sources was competitive to CAM methods for generating pseudolabels.