Continual learning in cross-modal retrieval

K Wang, L Herranz… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Multimodal representations and continual learning are two areas closely related to human
intelligence. The former considers the learning of shared representation spaces where …

Federated self-supervised learning of monocular depth estimators for autonomous vehicles

EFS Soares, CAV Campos - arxiv preprint arxiv:2310.04837, 2023 - arxiv.org
Image-based depth estimation has gained significant attention in recent research on
computer vision for autonomous vehicles in intelligent transportation systems. This focus …

[PDF][PDF] Continual Learning in Artificial Intelligence: A Review of Techniques, Metrics, and Real-World Applications

N Taygete, S Waldemar, H Salwa - 2025 - preprints.org
Continual learning (CL) is a critical paradigm in artificial intelligence that enables models to
learn sequentially from a stream of tasks while retaining previously acquired knowledge …

Corrosion Image Classification Using Deep Learning

H Nisar - 2024 - search.proquest.com
The slow deterioration of metal brought on by its chemical interactions with the environment
is known as corrosion. Material corrosion affects significant economic sectors and industries …

Continual Learning: Overcoming Catastrophic Forgetting for Adaptive AI Systems

H Salwa, N Burhan, E Rahel - Authorea Preprints - techrxiv.org
Continual learning is a fundamental challenge in artificial intelligence (AI) that aims to
enable models to learn from a continuous stream of data while retaining previously acquired …

Continual learning for hierarchical classification, few-shot recognition, and multi-modal learning

K Wang - 2022 - ddd.uab.cat
Deep learning has drastically changed computer vision in the past decades and achieved
great success in many applications, such as image classification, retrieval, detection, and …

Federated Lottery: Private and Communication-Efficient Learning of Personalized Networks

E Lin - 2022 - dash.harvard.edu
A promising approach to address privacy concerns, Federated learning (FL) enables
distributed training of machine learning (ML) models where user data remains on edge …