paper-with-me

홈 › Papers

Knowledge Restore and Transfer for Multi-label Class-Incremental Learning

2023-02-26 · ICCV 2023 1 · Songlin Dong, Haoyu Luo, Yuhang He, Xing Wei, Yihong Gong

Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although there have been many anti-forgetting methods to solve the problem of catastrophic forgetting in class-incremental learning, these methods have difficulty in solving the MLCIL problem due to label absence and information dilution. In this paper, we propose a knowledge restore and transfer (KRT) framework for MLCIL, which includes a dynamic pseudo-label (DPL) module to restore the old class knowledge and an incremental cross-attention(ICA) module to save session-specific knowledge and transfer old class knowledge to the new model sufficiently. Besides, we propose a token loss to jointly optimize the incremental cross-attention module. Experimental results on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on multi-label class-incremental learning tasks.

📄 PDF Abstract BibTeX arXiv:2302.13334

Code (1)

witdsl/krt-mlcil 공식 구현 pytorch

Tasks

class-incremental learningClass Incremental LearningIncremental LearningPseudo Label

Similar Papers 제목 키워드 기반

Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection

2018-08-07 · Meng Ye, Yuhong Guo

Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard…

image-classificationImage ClassificationMulti-Label Image ClassificationMulti-label zero-shot learning+2

Multi-Label Transfer Learning in Non-Stationary Data Streams

2025-09-09 · Honghui Du, Leandro Minku, Aonghus Lawlor, Huiyu Zhou arxiv

Label concepts in multi-label data streams often experience drift in non-stationary environments, either independently or in relation to other labels. Transferring knowledge between related labels can accelerate adaptati…

Multi-Label ClassificationTransfer Learning

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge

2020-07-30 · He Huang, Yuanwei Chen, Wei Tang, Wenhao Zheng 외

Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to …

ClassificationGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+3

Neyman-Pearson multiclass classification under label noise via empirical likelihood

2026-03-23 · Qiong Zhang, Qinglong Tian, Pengfei Li arxiv

In many classification problems, misclassification costs are highly asymmetric, while training labels are often corrupted due to measurement error, annotator variability, or adversarial noise. The Neyman-Pearson multicla…

Rebalancing Multi-Label Class-Incremental Learning

2024-08-22 · Kaile Du, Yifan Zhou, Fan Lyu, Yuyang Li 외

Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL ap…

class-incremental learningClass Incremental LearningIncremental LearningKnowledge Distillation