A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation

作     者：Feng Sun Ming-Kun Xie Sheng-Jun Huang Feng Sun;Ming-Kun Xie;Sheng-Jun Huang

作者机构：MIIT Key Laboratory of Pattern Analysis and Machine IntelligenceCollege of Computer Science and TechnologyNanjing University of AeronauticsandAstronauticsNanjing211106China 

出 版 物：《Machine Intelligence Research》 (机器智能研究（英文版）)

年 卷 期：2024年第21卷第4期

页      面：801-814页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 1002[医学-临床医学] 081104[工学-模式识别与智能系统] 08[工学] 100212[医学-眼科学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 10[医学] 

基　　金：supported by the National Key R&D Program of China 国家自然科学基金 江苏省自然科学基金 

主　　题：Partial multi-label image classification curriculum-based disambiguation consistency regularization label difficulty candidatelabel set. 

摘      要：In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy *** PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions,which unfortunately is unavailable in many real ***,because the objective function for disambiguation is usually elaborately designed on the whole training set,it can hardly be optimized in a deep model with stochastic gradient descent(SGD)on *** this paper,for the first time,we propose a deep model for PML to enhance the representation and discrimination *** the one hand,we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different *** the other hand,consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant *** experimental results on the commonly used benchmark datasets show that the proposed method significantlyoutperforms the SOTA methods.