16 citations · 24 across the 22 of their papers we have counts for
5 papers · 1 filter
MergeOver: Post-Training Token Merging for Recursive Vision Transformers
Junseo Kim, Uraz Odyurt, Amirreza Yousefzadeh
Vision Transformers (ViTs) demonstrate exceptional performance in computer vision but suffer from large parameter counts and quadratic computational complexity, severely limiting t…
NERVE: A Neuromorphic Vision and Radar Ensemble for Multi-Sensor Fusion Research
Omar Mansour, Pietro Martinello, Ethan Milon +4
We present NERVE (Neuromorphic Vision and Radar Ensemble), a multi-sensor dataset comprising 257 minutes of synchronized recordings from five sensors: two Dynamic Vision Sensors (D…
Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection
Shenqi Wang, Yingfu Xu, Amirreza Yousefzadeh +4
Leveraging the high temporal resolution and dynamic range, object detection with event cameras can enhance the performance and safety of automotive and robotics applications in rea…
TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision
Cina Arjmand, Yingfu Xu, Kevin Shidqi +6
Neuromorphic processors are well-suited for efficiently handling sparse events from event-based cameras. However, they face significant challenges in the growth of computing demand…
Training for temporal sparsity in deep neural networks, application in video processing
Amirreza Yousefzadeh, Manolis Sifalakis
Activation sparsity improves compute efficiency and resource utilization in sparsity-aware neural network accelerators. As the predominant operation in DNNs is multiply-accumulate…