no code implementations • 7 Jul 2022 • Huabin Diao, Gongyan Li, Shaoyun Xu, Yuexing Hao
For ResNet18 and MobileNetV2, the post-training quantization proposed in this paper only require 1, 024 training data and 10 minutes to complete the quantization process, which can achieve quantization performance on par with quantization aware training.
no code implementations • 3 Jul 2022 • Jinze Li, Yan Bai, Yihang Lou, Xiongkun Linghu, Jianzhong He, Shaoyun Xu, Tao Bai
The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem.
no code implementations • 26 Mar 2020 • Xiaoye Sun, Gongyan Li, Shaoyun Xu
Deep learning achieves excellent performance in many domains, so we not only apply it to the navel orange semantic segmentation task to solve the two problems of distinguishing defect categories and identifying the stem end and blossom end, but also propose a fastidious attention mechanism to further improve model performance.
no code implementations • 24 May 2019 • Xiaoye Sun, Gongyan Li, Shaoyun Xu
To accurately and efficiently distinguish the stem end and the blossom end of navel orange from its black spots, we propose a feature skyscraper detector (FSD) with low computational cost, compact architecture and high detection accuracy.