Search Results for author: Gongyan Li

Found 4 papers, 0 papers with code

Attention Round for Post-Training Quantization

no code implementations7 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.

Combinatorial Optimization Quantization

Fastidious Attention Network for Navel Orange Segmentation

no code implementations26 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.

Semantic Segmentation

FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange

no code implementations24 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.

Clustering

Multi-vision Attention Networks for On-line Red Jujube Grading

no code implementations31 Mar 2019 Xiaoye Sun, Liyan Ma, Gongyan Li

To solve the red jujube classification problem, this paper designs a convolutional neural network model with low computational cost and high classification accuracy.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.