← Search

Noor Ahmed

2 accepted papers

2024

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning

CVPR 2024highlight

Few-Shot Class-Incremental Learning (FSCIL) introduces a paradigm in which the problem space expands with limited data. FSCIL methods inherently face the challenge of catastrophic forgetting as data arrives incrementally making models susceptible to overwriting previously acquired knowledge. Moreove…

2024

iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning

ECCV 2024poster

"Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have recently addressed handling continual data streams. However, extending these methods to manage out-of-distribution (OOD) s…