Published in ECCV, 2024
We propose incremental neural mesh models that can be extended with new meshes over time
Recommended citation: Fischer, T., Liu, Y., Jesslen, A., Ahmed, N., Kaushik, P., Wang, A., ... & Ilg, E. (2024). iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning. arXiv preprint arXiv:2407.09271. https://arxiv.org/pdf/2407.09271
Published in CVPR, 2024
We propose the OrCo framework built on two core principles: orthogonality in the representation space, and contrastive learning.
Recommended citation: Ahmed, Noor, Anna Kukleva, and Bernt Schiele. "OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning." 41st IEEE/CVF Conference on Computer Vision and Pattern Recognition https://arxiv.org/pdf/2403.18550
Published in ICPRAM, 2023
In this work, we handle sewer inspection videos with severe challenges.
Recommended citation: Biswas, Rajarshi, Marcel Mutz, Piyush Pimplikar, Noor Ahmed, Dirk Werth. "Sewer-AI: Sustainable Automated Analysis of Real-World Sewer Videos Using DNNs." ICPRAM. 2023. https://pdfs.semanticscholar.org/d100/ce9a012034d0ab0b6ad5ee04ad0cc61071d4.pdf