Showing 2023Show all
2 papers · 1 filter
cs.CV2023
Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning
Jayateja Kalla, Soma Biswas
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catast…
cs.CV2023
S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning
Jayateja Kalla, Soma Biswas
Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes.…