Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry

07/20/2022
by   Yawen Cui, et al.
0

Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding the overfitting and catastrophic forgetting simultaneously. The current protocol of FSCIL is built by mimicking the general class-incremental learning setting, while it is not totally appropriate due to the different data configuration, i.e., novel classes are all in the limited data regime. In this paper, we rethink the configuration of FSCIL with the open-set hypothesis by reserving the possibility in the first session for incoming categories. To assign better performances on both close-set and open-set recognition to the model, Hyperbolic Reciprocal Point Learning module (Hyper-RPL) is built on Reciprocal Point Learning (RPL) with hyperbolic neural networks. Besides, for learning novel categories from limited labeled data, we incorporate a hyperbolic metric learning (Hyper-Metric) module into the distillation-based framework to alleviate the overfitting issue and better handle the trade-off issue between the preservation of old knowledge and the acquisition of new knowledge. The comprehensive assessments of the proposed configuration and modules on three benchmark datasets are executed to validate the effectiveness concerning three evaluation indicators.

READ FULL TEXT

page 1

page 2

research
01/24/2023

Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning

Given a model well-trained with a large-scale base dataset, Few-Shot Cla...
research
08/11/2022

Memorizing Complementation Network for Few-Shot Class-Incremental Learning

Few-shot Class-Incremental Learning (FSCIL) aims at learning new concept...
research
09/15/2022

On the Soft-Subnetwork for Few-shot Class Incremental Learning

Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothes...
research
06/12/2021

Knowledge Consolidation based Class Incremental Online Learning with Limited Data

We propose a novel approach for class incremental online learning in a l...
research
02/12/2023

Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters

The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn...
research
03/10/2022

Online Deep Metric Learning via Mutual Distillation

Deep metric learning aims to transform input data into an embedding spac...
research
07/29/2022

Conservative Generator, Progressive Discriminator: Coordination of Adversaries in Few-shot Incremental Image Synthesis

The capacity to learn incrementally from an online stream of data is an ...

Please sign up or login with your details

Forgot password? Click here to reset