TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning
Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. TLCE minimizes interference between old and new classes by mapping old class images to quasi-orthogonal prototypes using episodic training. It then ensembles diverse pre-trained models to better adapt to novel classes despite data imbalance. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningTransfer LearningSimilar Papers 제목 키워드 기반
Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles
Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to misle…
DiversityImage ClassificationDetection of depression on social networks using transformers and ensembles
As the impact of technology on our lives is increasing, we witness increased use of social media that became an essential tool not only for communication but also for sharing information with community about our thoughts…
Depression DetectionLanguage ModelingLanguage ModellingTransfer LearningSnapE -- Training Snapshot Ensembles of Link Prediction Models
Snapshot ensembles have been widely used in various fields of prediction. They allow for training an ensemble of prediction models at the cost of training a single one. They are known to yield more robust predictions by …
Knowledge GraphsLink PredictionPredictionEnsembles of Random Sphere Cover Classifiers
We propose and evaluate alternative ensemble schemes for a new instance based learning classifier, the Randomised Sphere Cover (RSC) classifier. RSC fuses instances into spheres, then bases classification on distance to …
AttributeTo Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
Transfer learning and ensembling are two popular techniques for improving the performance and robustness of neural networks. Due to the high cost of pre-training, ensembles of models fine-tuned from a single pre-trained …
DiversityTransfer Learning