5 papers · 1 filter
CHOSEN: Compilation to Hardware Optimization Stack for Efficient Vision Transformer Inference
Mohammad Erfan Sadeghi, Arash Fayyazi, Suhas Somashekar +2
Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechani…
FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair
Arya Fayyazi, Mehdi Kamal, Massoud Pedram
We introduce FAIR-SIGHT, an innovative post-hoc framework designed to ensure fairness in computer vision systems by combining conformal prediction with a dynamic output repair mech…
PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers
Mohammad Erfan Sadeghi, Arash Fayyazi, Seyedarmin Azizi +1
The deployment of Vision Transformers (ViTs) on hardware platforms, specially Field-Programmable Gate Arrays (FPGAs), presents many challenges, which are mainly due to the substant…
Enhancing Layout Hotspot Detection Efficiency with YOLOv8 and PCA-Guided Augmentation
Dongyang Wu, Siyang Wang, Mehdi Kamal +1
In this paper, we present a YOLO-based framework for layout hotspot detection, aiming to enhance the efficiency and performance of the design rule checking (DRC) process. Our appro…
Training-Free Acceleration of ViTs with Delayed Spatial Merging
Jung Hwan Heo, Seyedarmin Azizi, Arash Fayyazi +1
Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-…