Contrastive Supervised Distillation for Continual Representation Learning

Autor:	Barletti, Tommaso, Biondi, Niccolo', Pernici, Federico, Bruni, Matteo, Del Bimbo, Alberto
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning
Zdroj:	ICIAP 2021
Druh dokumentu:	Working Paper
DOI:	10.1007/978-3-031-06427-2_50
Popis:	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 by outperforming current state-of-the-art methods. Our results also provide further evidence that feature forgetting evaluated in visual retrieval tasks is not as catastrophic as in classification tasks. Code at: https://github.com/NiccoBiondi/ContrastiveSupervisedDistillation. Comment: Paper published as Oral and awarded as Best Student Paper at ICIAP21
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2205.05476 Zobrazit plný text záznamu View this record from Arxiv