Unsupervised Class-Incremental Learning Through Confusion
While many works on Continual Learning have shown promising results for mitigating catastrophic forgetting, they have relied on supervised training. To successfully learn in a label-agnostic incremental setting, a model must distinguish between learned and novel classes to properly include samples for training. We introduce a novelty detection method that leverages network confusion caused by training incoming data as a new class. We found that incorporating a class-imbalance during this detection method substantially enhances performance. The effectiveness of our approach is demonstrated across a set of image classification benchmarks: MNIST, SVHN, CIFAR-10, CIFAR-100, and CRIB.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningContinual Learningimage-classificationImage ClassificationIncremental LearningNovelty Detectionunsupervised class-incremental learningSimilar Papers 제목 키워드 기반
Scheduling to Learn In An Unsupervised Online Streaming Model
An unsupervised online streaming model is considered where samples arrive in an online fashion over $T$ slots. There are $M$ classifiers, whose confusion matrices are unknown a priori. In each slot, at most one sample ca…
SchedulingTask Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
In class-incremental learning (class-IL), models must classify all previously seen classes at test time without task-IDs, leading to task confusion. Despite being a key challenge, task confusion lacks a theoretical under…
class-incremental learningClass Incremental LearningIncremental LearningReducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use prototypes of classes during incremental up…
class-incremental learningClass Incremental LearningIncremental LearningResolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning
The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framewor…
class-incremental learningClass Incremental LearningIncremental LearningIncremental Learning on CIFAR100-B0(5steps of 20 classes)+1Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class
Class-incremental semantic segmentation aims to incrementally learn new classes while maintaining the capability to segment old ones, and suffers catastrophic forgetting since the old-class labels are unavailable. Mo…
Class-Incremental Semantic SegmentationDecoderKnowledge DistillationSegmentation+1