Picture for Jiayuan Fan

Jiayuan Fan

Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

May 18, 2023
Chong Yu, Tao Chen, Zhongxue Gan, Jiayuan Fan

Figure 1 for Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

Figure 2 for Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

Figure 3 for Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

Figure 4 for Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

* Accepted to CVPR 2023, 11 pages, 6 figures

Access Paper or Ask Questions

What Makes for Effective Few-shot Point Cloud Classification?

Mar 31, 2023
Chuangguan Ye, Hongyuan Zhu, Yongbin Liao, Yanggang Zhang, Tao Chen, Jiayuan Fan

Figure 1 for What Makes for Effective Few-shot Point Cloud Classification?

Figure 2 for What Makes for Effective Few-shot Point Cloud Classification?

Figure 3 for What Makes for Effective Few-shot Point Cloud Classification?

Figure 4 for What Makes for Effective Few-shot Point Cloud Classification?

* Accepted by WACV 2022. arXiv admin note: text overlap with arXiv:2303.18210

Access Paper or Ask Questions

Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

Mar 21, 2023
Hancheng Ye, Bo Zhang, Tao Chen, Jiayuan Fan, Bin Wang

Figure 1 for Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

Figure 2 for Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

Figure 3 for Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

Figure 4 for Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

* Accepted for publication in T-PAMI, our code is available at http://www.github.com/HankYe/PAGCP.git

Access Paper or Ask Questions

A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

Feb 23, 2023
Lin Zhan, Jiayuan Fan, Peng Ye, Jianjian Cao

Figure 1 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

Figure 2 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

Figure 3 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

Figure 4 for A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification

* Accepted by 48th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)

Access Paper or Ask Questions

JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

Feb 20, 2023
Jiamu Sheng, Jiayuan Fan, Peng Ye, Jianjian Cao

Figure 1 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

Figure 2 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

Figure 3 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

Figure 4 for JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment

* Accepted by 48th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)

Access Paper or Ask Questions

Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

Jul 02, 2022
Bo Zhang, Jiakang Yuan, Baopu Li, Tao Chen, Jiayuan Fan, Botian Shi

Figure 1 for Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

Figure 2 for Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

Figure 3 for Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

Figure 4 for Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

* Accepted by ACM MM-2022

Access Paper or Ask Questions