10 papers
Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers
Ibrahim Batuhan Akkaya, Kishaan Jeeveswaran, Bahram Zonooz +1
The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources. Drawing ins…
PhysVid: Physics Aware Local Conditioning for Generative Video Models
Saurabh Pathak, Elahe Arani, Mykola Pechenizkiy +1
Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely…
Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation
Prashant Shivaram Bhat, Shakib Yazdani, Elahe Arani +1
Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge when learning new tasks. Param…
Depth3DLane: Fusing Monocular 3D Lane Detection with Self-Supervised Monocular Depth Estimation
Max van den Hoven, Kishaan Jeeveswaran, Pieter Piscaer +3
Monocular 3D lane detection is essential for autonomous driving, but challenging due to the inherent lack of explicit spatial information. Multi-modal approaches rely on expensive…
Continual Learning Beyond Experience Rehearsal and Full Model Surrogates
Prashant Bhat, Laurens Niesten, Elahe Arani +1
Continual learning (CL) has remained a significant challenge for deep neural networks as learning new tasks erases previously acquired knowledge, either partially or completely. Ex…
Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
Kishaan Jeeveswaran, Elahe Arani, Bahram Zonooz
Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoid…