点击次数：

论文类型：论文集

第一作者：Xiang Xiang

合写作者：Yuwen Tan,QIan Wan,Jing Ma,Alan L. Yuille,Gregory D. Hager

发表刊物：Proceedings of European Conference on Computer Vision (ECCV) 2022

收录刊物：EI

刊物所在地：德国

学科门类：工学

一级学科：控制科学与工程

文献类型：C

发表时间：2022-07-06

摘要：Different from fine-tuning models pre-trained on a large-scale dataset of preset classes, class-incremental learning (CIL) aims to recognize novel classes over time without forgetting pre-trained classes. However, a given model will be challenged by test images with finer-grained classes, e.g., a basenji is at most recognized as a dog. Such images form a new training set (i.e., support set) so that the incremental model is hoped to recognize a basenji (i.e., query) as a basenji next time. This paper formulates such a hybrid natural problem of coarse-to-fine few-shot (C2FS) recognition as a CIL problem named C2FSCIL, and proposes a simple, effective, and theoretically-sound strategy Knowe: to learn, normalize, and freeze a classifier's weights from fine labels, once learning an embedding space contrastively from coarse labels. Besides, as CIL aims at a stability-plasticity balance, new overall performance metrics are proposed. In that sense, on CIFAR-100, BREEDS, and tieredImageNet, Knowe outperforms all recent relevant CIL or FSCIL methods.