2024/07/26 by Gihwan Kim, Kim, Gihwan, Jemin Lee +6 · 2 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #CCD and CMOS Imaging Sensors #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrared Target Detection Methodologies #Neural Networks and Applications
paper · pdf · doi:10.48550/arxiv.2407.18437
openalex publication_date 2024/07/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The majority of quantization methods have been proposed to reduce the model size of Vision Transformers, yet most of them have overlooked the quantization of non-linear operations. Only a few works have addressed quantization for non-linear operations, but they applied a single quantization method across all non-linear operations. We believe that this can be further improved by employing a different quantization method for each non-linear operation. Therefore, to assign the most error-minimizing quantization method from the known methods to each non-linear layer, we propose a mixed non-linear quantization that considers layer-wise quantization sensitivity measured by SQNR difference metric. The results show that our method outperforms I-BERT, FQ-ViT, and I-ViT in both 8-bit and 6-bit settings for ViT, DeiT, and Swin models by an average of 0.6%p and 19.6%p, respectively. Our method outperforms I-BERT and I-ViT by 0.6%p and 20.8%p, respectively, when training time is limited. We plan to release our code at https://gitlab.com/ones-ai/mixed-non-linear-quantization.