Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry
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.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningMetric LearningOpen Set LearningSimilar Papers 제목 키워드 기반
On the Soft-Subnetwork for Few-shot Class Incremental Learning
Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we propo…
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningIncremental Few-Shot Object Detection
Most existing object detection methods rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements substantially limit their scalability to open…
Few-Shot LearningFew-Shot Object DetectionIncremental LearningMeta-Learning+3Rethinking Few-shot Class-incremental Learning: Learning from Yourself
Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL use…
class-incremental learningClass Incremental LearningContinual LearningFew-Shot Class-Incremental Learning+1Few-Shot Batch Incremental Road Object Detection via Detector Fusion
Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this…
Few-Shot Learningobject-detectionObject DetectionContinual Learning in Open-vocabulary Classification with Complementary Memory Systems
We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition. Specifically, we propo…
Continual Learningimage-classificationImage ClassificationOpen Vocabulary Image Classification