6 papers
MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities
Shishir Muralidhara, Didier Stricker, René Schuster +1
Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Expert-based learning, in which t…
SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning
Shishir Muralidhara, Didier Stricker, René Schuster
Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting. These factors significantly limit…
CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation
Shishir Muralidhara, Didier Stricker, René Schuster
In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of task…
Domain-Incremental Semantic Segmentation for Autonomous Driving under Adverse Driving Conditions
Shishir Muralidhara, René Schuster, Didier Stricker
Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal condi…
Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation
Niharika Hegde, Shishir Muralidhara, René Schuster +1
In autonomous driving, environment perception has significantly advanced with the utilization of deep learning techniques for diverse sensors such as cameras, depth sensors, or inf…
CLEO: Continual Learning of Evolving Ontologies
Shishir Muralidhara, Saqib Bukhari, Georg Schneider +2
Continual learning (CL) addresses the problem of catastrophic forgetting in neural networks, which occurs when a trained model tends to overwrite previously learned information, wh…