.png){kind=icon}
.png){kind=icon}
Return
Graph-based interactive knowledge distillation for social relation continual learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129860.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As multimedia advances, there is a growing need for machines to adeptly understand diverse social relations. Traditional methods for recognizing these relations, which are limited to a fixed number of classes, are illequipped for continual learning as new social interactions emerge. To address this prob-lem, we propose a pioneering Graph-based Interactive Knowledge Distillation (GI-KD) method for social relation continual learning. GI-KD, embedded in a class incremental learning structure, creates a balanced system where previously learned social relations and new knowledge are positioned at either end of the scale. The old and new knowledge is learned dynamically by adjusting the tilt of the balance. To achieve this balance, we propose a novel Libra loss function, which evaluate the relative contribution of old and new information and thus guides the adaptive fine-tuning of the model. We evaluate the GI-KD on three public social relation recognition (SRR) datasets, under different data distribution strategies. Our method shows a remarkable average 3.6% increase in incremental accuracy over current CIL techniques, effectively reducing catastrophic forgetting. Furthermore, GI-KD improves mAP and Acc by 4.6%, 5.4%, and 4.5%, respectively, compared to current CIL techniques, highlighting its strength in both continual learning and SRR.
Keywords:
Social relation recognition
Continual learning
Class incremental learning
Graph-based interactive knowledge distillation
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W