Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Meng, Tianjian"'
It is commonly believed that high internal resolution combined with expensive operations (e.g. atrous convolutions) are necessary for accurate semantic segmentation, resulting in slow speed and large memory usage. In this paper, we question this beli
Externí odkaz:
http://arxiv.org/abs/2203.12683
Autor:
Li, Yingwei, Yu, Adams Wei, Meng, Tianjian, Caine, Ben, Ngiam, Jiquan, Peng, Daiyi, Shen, Junyang, Wu, Bo, Lu, Yifeng, Zhou, Denny, Le, Quoc V., Yuille, Alan, Tan, Mingxing
Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to existing
Externí odkaz:
http://arxiv.org/abs/2203.08195
In recent years, great success has been witnessed in building problem-specific deep networks from unrolling iterative algorithms, for solving inverse problems and beyond. Unrolling is believed to incorporate the model-based prior with the learning ca
Externí odkaz:
http://arxiv.org/abs/2104.04110
Autor:
Zhou, Yanqi, Dong, Xuanyi, Akin, Berkin, Tan, Mingxing, Peng, Daiyi, Meng, Tianjian, Yazdanbakhsh, Amir, Huang, Da, Narayanaswami, Ravi, Laudon, James
Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed hardware. And the
Externí odkaz:
http://arxiv.org/abs/2102.08619
Autor:
Qian, Rui, Meng, Tianjian, Gong, Boqing, Yang, Ming-Hsuan, Wang, Huisheng, Belongie, Serge, Cui, Yin
We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips from the sa
Externí odkaz:
http://arxiv.org/abs/2008.03800
Autor:
Zhou, Denny, Ye, Mao, Chen, Chen, Meng, Tianjian, Tan, Mingxing, Song, Xiaodan, Le, Quoc, Liu, Qiang, Schuurmans, Dale
For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational ef
Externí odkaz:
http://arxiv.org/abs/2007.00811
Autor:
Shao, Wenqi, Meng, Tianjian, Li, Jingyu, Zhang, Ruimao, Li, Yudian, Wang, Xiaogang, Luo, Ping
Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different normalizers
Externí odkaz:
http://arxiv.org/abs/1903.03793