Alert button
Picture for Junjie Yan

Junjie Yan

Alert button

PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection

Nov 29, 2023
Weixin Mao, Tiancai Wang, Diankun Zhang, Junjie Yan, Osamu Yoshie

Viaarxiv icon

Cross Modal Transformer via Coordinates Encoding for 3D Object Dectection

Jan 03, 2023
Junjie Yan, Yingfei Liu, Jianjian Sun, Fan Jia, Shuailin Li, Tiancai Wang, Xiangyu Zhang

Figure 1 for Cross Modal Transformer via Coordinates Encoding for 3D Object Dectection
Figure 2 for Cross Modal Transformer via Coordinates Encoding for 3D Object Dectection
Figure 3 for Cross Modal Transformer via Coordinates Encoding for 3D Object Dectection
Figure 4 for Cross Modal Transformer via Coordinates Encoding for 3D Object Dectection
Viaarxiv icon

PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

Jun 02, 2022
Yingfei Liu, Junjie Yan, Fan Jia, Shuailin Li, Qi Gao, Tiancai Wang, Xiangyu Zhang, Jian Sun

Figure 1 for PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Figure 2 for PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Figure 3 for PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Figure 4 for PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Viaarxiv icon

cosFormer: Rethinking Softmax in Attention

Feb 17, 2022
Zhen Qin, Weixuan Sun, Hui Deng, Dongxu Li, Yunshen Wei, Baohong Lv, Junjie Yan, Lingpeng Kong, Yiran Zhong

Figure 1 for cosFormer: Rethinking Softmax in Attention
Figure 2 for cosFormer: Rethinking Softmax in Attention
Figure 3 for cosFormer: Rethinking Softmax in Attention
Figure 4 for cosFormer: Rethinking Softmax in Attention
Viaarxiv icon

One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data

Nov 24, 2021
Yujie Wang, Junqin Huang, Mengya Gao, Yichao Wu, Zhenfei Yin, Ding Liang, Junjie Yan

Figure 1 for One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Figure 2 for One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Figure 3 for One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Figure 4 for One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Viaarxiv icon

INTERN: A New Learning Paradigm Towards General Vision

Nov 16, 2021
Jing Shao, Siyu Chen, Yangguang Li, Kun Wang, Zhenfei Yin, Yinan He, Jianing Teng, Qinghong Sun, Mengya Gao, Jihao Liu, Gengshi Huang, Guanglu Song, Yichao Wu, Yuming Huang, Fenggang Liu, Huan Peng, Shuo Qin, Chengyu Wang, Yujie Wang, Conghui He, Ding Liang, Yu Liu, Fengwei Yu, Junjie Yan, Dahua Lin, Xiaogang Wang, Yu Qiao

Figure 1 for INTERN: A New Learning Paradigm Towards General Vision
Figure 2 for INTERN: A New Learning Paradigm Towards General Vision
Figure 3 for INTERN: A New Learning Paradigm Towards General Vision
Figure 4 for INTERN: A New Learning Paradigm Towards General Vision
Viaarxiv icon

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

Nov 05, 2021
Yuhang Li, Mingzhu Shen, Jian Ma, Yan Ren, Mingxin Zhao, Qi Zhang, Ruihao Gong, Fengwei Yu, Junjie Yan

Figure 1 for MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Figure 2 for MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Figure 3 for MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Figure 4 for MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Viaarxiv icon

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Oct 11, 2021
Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, Junjie Yan

Figure 1 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Figure 2 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Figure 3 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Figure 4 for Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Viaarxiv icon

BN-NAS: Neural Architecture Search with Batch Normalization

Aug 16, 2021
Boyu Chen, Peixia Li, Baopu Li, Chen Lin, Chuming Li, Ming Sun, Junjie Yan, Wanli Ouyang

Figure 1 for BN-NAS: Neural Architecture Search with Batch Normalization
Figure 2 for BN-NAS: Neural Architecture Search with Batch Normalization
Figure 3 for BN-NAS: Neural Architecture Search with Batch Normalization
Figure 4 for BN-NAS: Neural Architecture Search with Batch Normalization
Viaarxiv icon

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Aug 13, 2021
Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Junjie Yan, Wanli Ouyang

Figure 1 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Figure 2 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Figure 3 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Figure 4 for Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Viaarxiv icon