Knowledge Restore and Transfer for Multi-label Class-Incremental Learning
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.
Code (1)
Tasks
class-incremental learningClass Incremental LearningIncremental LearningPseudo LabelSimilar Papers 제목 키워드 기반
Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection
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+2Multi-Label Transfer Learning in Non-Stationary Data Streams
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 LearningMulti-label Zero-shot Classification by Learning to Transfer from External Knowledge
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+3Neyman-Pearson multiclass classification under label noise via empirical likelihood
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
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