Contrastive Supervised Distillation for Continual Representation Learning. (arXiv:2205.05476v1 [cs.CV])

Web: http://arxiv.org/abs/2205.05476

In this paper, we propose a novel training procedure for the continual
representation learning problem in which a neural network model is sequentially
learned to alleviate catastrophic forgetting in visual search tasks. Our
method, called Contrastive Supervised Distillation (CSD), reduces feature
forgetting while learning discriminative features. This is achieved by
leveraging labels information in a distillation setting in which the student
model is contrastively learned from the teacher model. Extensive experiments
show that CSD performs favorably in mitigating catastrophic forgetting …

arxiv continual cv distillation learning representation representation learning