no code implementations • 5 Sep 2023 • Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra
Results demonstrate that our TODM Supernet either matches or surpasses the performance of manually tuned models by up to a relative of 3% better in word error rate (WER), while efficiently keeping the cost of training many models at a small constant.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 8 Jun 2023 • Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra
In addition, the proposed method achieves the SOTA performance in NAS for building fast machine translation models, yielding better latency-BLEU tradeoff compared to HAT, state-of-the-art NAS for MT.
no code implementations • 9 Nov 2022 • Haichuan Yang, Zhaojun Yang, Li Wan, Biqiao Zhang, Yangyang Shi, Yiteng Huang, Ivaylo Enchev, Limin Tang, Raziel Alvarez, Ming Sun, Xin Lei, Raghuraman Krishnamoorthi, Vikas Chandra
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting.
no code implementations • 25 Jul 2022 • Chunxi Liu, Yuan Shangguan, Haichuan Yang, Yangyang Shi, Raghuraman Krishnamoorthi, Ozlem Kalinli
There is growing interest in unifying the streaming and full-context automatic speech recognition (ASR) networks into a single end-to-end ASR model to simplify the model training and deployment for both use cases.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 2 Jun 2022 • Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin
Efficient deep neural network (DNN) models equipped with compact operators (e. g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e. g., the total number of weights/operations) while maintaining a decent model accuracy.
1 code implementation • 18 Nov 2021 • Haoqi Fan, Tullie Murrell, Heng Wang, Kalyan Vasudev Alwala, Yanghao Li, Yilei Li, Bo Xiong, Nikhila Ravi, Meng Li, Haichuan Yang, Jitendra Malik, Ross Girshick, Matt Feiszli, Aaron Adcock, Wan-Yen Lo, Christoph Feichtenhofer
We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised learning, and low-level processing.
no code implementations • 2 Nov 2021 • Cole Hawkins, Haichuan Yang, Meng Li, Liangzhen Lai, Vikas Chandra
Low-rank tensor compression has been proposed as a promising approach to reduce the memory and compute requirements of neural networks for their deployment on edge devices.
no code implementations • 15 Oct 2021 • Haichuan Yang, Yuan Shangguan, Dilin Wang, Meng Li, Pierce Chuang, Xiaohui Zhang, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 9 Jul 2021 • Dilin Wang, Yuan Shangguan, Haichuan Yang, Pierce Chuang, Jiatong Zhou, Meng Li, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra
We apply noisy training to improve both dense and sparse state-of-the-art Emformer models and observe consistent WER reduction.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
2 code implementations • ECCV 2020 • Haotao Wang, Shupeng Gui, Haichuan Yang, Ji Liu, Zhangyang Wang
Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications, and recently start to be deployed to resource-constrained mobile devices.
1 code implementation • CVPR 2020 • Haichuan Yang, Shupeng Gui, Yuhao Zhu, Ji Liu
A key parameter that all existing compression techniques are sensitive to is the compression ratio (e. g., pruning sparsity, quantization bitwidth) of each layer.
2 code implementations • NeurIPS 2019 • Shupeng Gui, Haotao Wang, Chen Yu, Haichuan Yang, Zhangyang Wang, Ji Liu
Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss.
2 code implementations • CVPR 2019 • Haichuan Yang, Yuhao Zhu, Ji Liu
The energy estimate model allows us to formulate DNN compression as a constrained optimization that minimizes the DNN loss function over the energy constraint.
1 code implementation • ICLR 2019 • Carson Eisenach, Haichuan Yang, Ji Liu, Han Liu
In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter.
1 code implementation • ICLR 2019 • Haichuan Yang, Yuhao Zhu, Ji Liu
Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time.
no code implementations • 16 Apr 2018 • Hongyu Xu, Zhangyang Wang, Haichuan Yang, Ding Liu, Ji Liu
The thresholded feature has recently emerged as an extremely efficient, yet rough empirical approximation, of the time-consuming sparse coding inference process.
no code implementations • 18 Mar 2018 • Ke Ren, Haichuan Yang, Yu Zhao, Mingshan Xue, Hongyu Miao, Shuai Huang, Ji Liu
The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large volume of "unlabeled" samples that may contain both positive and negative samples.
1 code implementation • ICLR 2018 • Jiechao Xiong, Qing Wang, Zhuoran Yang, Peng Sun, Yang Zheng, Lei Han, Haobo Fu, Xiangru Lian, Carson Eisenach, Haichuan Yang, Emmanuel Ekwedike, Bei Peng, Haoyue Gao, Tong Zhang, Ji Liu, Han Liu
Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space.
no code implementations • ICML 2017 • Haichuan Yang, Shupeng Gui, Chuyang Ke, Daniel Stefankovic, Ryohei Fujimaki, Ji Liu
The cardinality constraint is an intrinsic way to restrict the solution structure in many domains, for example, sparse learning, feature selection, and compressed sensing.
no code implementations • CVPR 2016 • Haichuan Yang, Yijun Huang, Lam Tran, Ji Liu, Shuai Huang
In this paper, we proposed a general bilevel exclusive sparsity formulation to pursue the diversity by restricting the overall sparsity and the sparsity in each group.
no code implementations • CVPR 2014 • Haichuan Yang, Xiao Bai, Jun Zhou, Peng Ren, Zhihong Zhang, Jian Cheng
Hashing is very useful for fast approximate similarity search on large database.