Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation



Jiaqi Gu , Hyoukjun Kwon , Dilin Wang , Wei Ye , Meng Li , Yu-Hsin Chen , Liangzhen Lai , Vikas Chandra , David Z. Pan

* 8 pages 

   Access Paper or Ask Questions

Temporally Consistent Online Depth Estimation in Dynamic Scenes



Zhaoshuo Li , Wei Ye , Dilin Wang , Francis X. Creighton , Russell H. Taylor , Ganesh Venkatesh , Mathias Unberath


   Access Paper or Ask Questions

HRViT: Multi-Scale High-Resolution Vision Transformer



Jiaqi Gu , Hyoukjun Kwon , Dilin Wang , Wei Ye , Meng Li , Yu-Hsin Chen , Liangzhen Lai , Vikas Chandra , David Z. Pan

* 8 pages 

   Access Paper or Ask Questions

Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet



Haichuan Yang , Yuan Shangguan , Dilin Wang , Meng Li , Pierce Chuang , Xiaohui Zhang , Ganesh Venkatesh , Ozlem Kalinli , Vikas Chandra


   Access Paper or Ask Questions

Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution



Yangyang Shi , Chunyang Wu , Dilin Wang , Alex Xiao , Jay Mahadeokar , Xiaohui Zhang , Chunxi Liu , Ke Li , Yuan Shangguan , Varun Nagaraja , Ozlem Kalinli , Mike Seltzer

* 5 pages, 3 figures, submit to ICASSP 2022 

   Access Paper or Ask Questions

Noisy Training Improves E2E ASR for the Edge



Dilin Wang , Yuan Shangguan , Haichuan Yang , Pierce Chuang , Jiatong Zhou , Meng Li , Ganesh Venkatesh , Ozlem Kalinli , Vikas Chandra


   Access Paper or Ask Questions

Improve Vision Transformers Training by Suppressing Over-smoothing



Chengyue Gong , Dilin Wang , Meng Li , Vikas Chandra , Qiang Liu

* preprint 

   Access Paper or Ask Questions

AlphaNet: Improved Training of Supernet with Alpha-Divergence



Dilin Wang , Chengyue Gong , Meng Li , Qiang Liu , Vikas Chandra


   Access Paper or Ask Questions

AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence



Chengyue Gong , Dilin Wang , Qiang Liu

* preprint 

   Access Paper or Ask Questions

KeepAugment: A Simple Information-Preserving Data Augmentation Approach



Chengyue Gong , Dilin Wang , Meng Li , Vikas Chandra , Qiang Liu


   Access Paper or Ask Questions

1
2
3
>>