61 citations · 71 across the 4 of their papers we have counts for
4 papers
Accelerating Data Preprocessing for Efficient Vision Model Inference on Jetson Edge Device
Tian Chen, Nawras Alnaasan, Jinghan Yao +4
Data preprocessing is a crucial part of deep learning workflows on edge devices. However, decoding data saved in JPEG format is very compute-intensive and occupies a major portion…
Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference
Jinghan Yao, Nawras Alnaasan, Tian Chen +4
Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on thes…
SOFT: Softmax-free Transformer with Linear Complexity
Jiachen Lu, Jinghan Yao, Junge Zhang +6
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employmen…
Single Pixel Reconstruction for One-stage Instance Segmentation
Jun Yu, Jinghan Yao, Jian Zhang +2
Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches…