no code implementations • 28 Mar 2024 • Avinash Paliwal, Wei Ye, Jinhui Xiong, Dmytro Kotovenko, Rakesh Ranjan, Vikas Chandra, Nima Khademi Kalantari
The field of 3D reconstruction from images has rapidly evolved in the past few years, first with the introduction of Neural Radiance Field (NeRF) and more recently with 3D Gaussian Splatting (3DGS).
no code implementations • 22 Feb 2024 • Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra
The resultant models, denoted as MobileLLM-LS, demonstrate a further accuracy enhancement of 0. 7%/0. 8% than MobileLLM 125M/350M.
no code implementations • 20 Feb 2024 • Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra
This study delves into how weight parameters in speech recognition models influence the overall power consumption of these models.
no code implementations • 20 Feb 2024 • Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, Rakesh Ranjan
MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time.
no code implementations • 31 Dec 2023 • Peihao Wang, Zhiwen Fan, Dejia Xu, Dilin Wang, Sreyas Mohan, Forrest Iandola, Rakesh Ranjan, Yilei Li, Qiang Liu, Zhangyang Wang, Vikas Chandra
In this paper, we reveal that the gradient estimation in score distillation is inherent to high variance.
no code implementations • 31 Dec 2023 • Peihao Wang, Dejia Xu, Zhiwen Fan, Dilin Wang, Sreyas Mohan, Forrest Iandola, Rakesh Ranjan, Yilei Li, Qiang Liu, Zhangyang Wang, Vikas Chandra
In this paper, we reveal that the existing score distillation-based text-to-3D generation frameworks degenerate to maximal likelihood seeking on each view independently and thus suffer from the mode collapse problem, manifesting as the Janus artifact in practice.
no code implementations • 11 Dec 2023 • Balakrishnan Varadarajan, Bilge Soran, Forrest Iandola, Xiaoyu Xiang, Yunyang Xiong, Chenchen Zhu, Raghuraman Krishnamoorthi, Vikas Chandra
Finally, when a user clicks on an object, they typically expect all related pieces of the object to be segmented.
1 code implementation • 1 Dec 2023 • Yunyang Xiong, Bala Varadarajan, Lemeng Wu, Xiaoyu Xiang, Fanyi Xiao, Chenchen Zhu, Xiaoliang Dai, Dilin Wang, Fei Sun, Forrest Iandola, Raghuraman Krishnamoorthi, Vikas Chandra
On segment anything task such as zero-shot instance segmentation, our EfficientSAMs with SAMI-pretrained lightweight image encoders perform favorably with a significant gain (e. g., ~4 AP on COCO/LVIS) over other fast SAM models.
Ranked #3 on Zero-Shot Instance Segmentation on LVIS v1.0 val
no code implementations • 1 Nov 2023 • Ernie Chang, Pin-Jie Lin, Yang Li, Sidd Srinivasan, Gael Le Lan, David Kant, Yangyang Shi, Forrest Iandola, Vikas Chandra
We show that the framework enhanced the audio quality across the set of collected user prompts, which were edited with reference to the training captions as exemplars.
no code implementations • 1 Nov 2023 • Ernie Chang, Sidd Srinivasan, Mahi Luthra, Pin-Jie Lin, Varun Nagaraja, Forrest Iandola, Zechun Liu, Zhaoheng Ni, Changsheng Zhao, Yangyang Shi, Vikas Chandra
Text-to-audio generation (TTA) produces audio from a text description, learning from pairs of audio samples and hand-annotated text.
1 code implementation • 14 Oct 2023 • Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, Mohamed Elhoseiny
Motivated by this, we target to build a unified interface for completing many vision-language tasks including image description, visual question answering, and visual grounding, among others.
Ranked #10 on Visual Question Answering on BenchLMM
no code implementations • 19 Sep 2023 • Xinhao Mei, Varun Nagaraja, Gael Le Lan, Zhaoheng Ni, Ernie Chang, Yangyang Shi, Vikas Chandra
A prevalent problem in V2A generation is the misalignment of generated audio with the visible actions in the video.
no code implementations • 19 Sep 2023 • Zhaoheng Ni, Sravya Popuri, Ning Dong, Kohei Saijo, Xiaohui Zhang, Gael Le Lan, Yangyang Shi, Vikas Chandra, Changhan Wang
High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 15 Sep 2023 • Yangyang Shi, Gael Le Lan, Varun Nagaraja, Zhaoheng Ni, Xinhao Mei, Ernie Chang, Forrest Iandola, Yang Liu, Vikas Chandra
This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training.
no code implementations • 15 Sep 2023 • Gael Le Lan, Varun Nagaraja, Ernie Chang, David Kant, Zhaoheng Ni, Yangyang Shi, Forrest Iandola, Vikas Chandra
In language modeling based music generation, a generated waveform is represented by a sequence of hierarchical token stacks that can be decoded either in an auto-regressive manner or in parallel, depending on the codebook patterns.
no code implementations • 14 Sep 2023 • Yang Li, Liangzhen Lai, Yuan Shangguan, Forrest N. Iandola, Zhaoheng Ni, Ernie Chang, Yangyang Shi, Vikas Chandra
Instead, the bottleneck lies in the linear projection layers of multi-head attention and feedforward networks, constituting a substantial portion of the model size and contributing significantly to computation, memory, and power usage.
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
1 code implementation • 1 Jul 2023 • Ernie Chang, Muhammad Hassan Rashid, Pin-Jie Lin, Changsheng Zhao, Vera Demberg, Yangyang Shi, Vikas Chandra
Knowing exactly how many data points need to be labeled to achieve a certain model performance is a hugely beneficial step towards reducing the overall budgets for annotation.
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 • 29 May 2023 • Zechun Liu, Barlas Oguz, Changsheng Zhao, Ernie Chang, Pierre Stock, Yashar Mehdad, Yangyang Shi, Raghuraman Krishnamoorthi, Vikas Chandra
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits.
no code implementations • 12 Dec 2022 • Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties.
no code implementations • 7 Dec 2022 • Seah Kim, Hyoukjun Kwon, Jinook Song, Jihyuck Jo, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra
Such dynamic behaviors introduce new challenges to the system software in an ML system since the overall system load is not completely predictable, unlike traditional ML workloads.
1 code implementation • CVPR 2023 • Lemeng Wu, Dilin Wang, Chengyue Gong, Xingchao Liu, Yunyang Xiong, Rakesh Ranjan, Raghuraman Krishnamoorthi, Vikas Chandra, Qiang Liu
We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods.
no code implementations • 16 Nov 2022 • Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi
We hope that our work will stimulate research and lead to the development of a new generation of ML systems for XR use cases.
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.
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.
no code implementations • 29 Mar 2022 • Jay Mahadeokar, Yangyang Shi, Ke Li, Duc Le, Jiedan Zhu, Vikas Chandra, Ozlem Kalinli, Michael L Seltzer
Streaming ASR with strict latency constraints is required in many speech recognition applications.
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.
1 code implementation • CVPR 2022 • Jiaqi Gu, Hyoukjun Kwon, Dilin Wang, Wei Ye, Meng Li, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra, David Z. Pan
Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs.
Ranked #25 on Semantic Segmentation on Cityscapes val
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
1 code implementation • ICLR 2022 • Chengyue Gong, Dilin Wang, Meng Li, Xinlei Chen, Zhicheng Yan, Yuandong Tian, Qiang Liu, Vikas Chandra
In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence.
Ranked #7 on Neural Architecture Search on ImageNet
no code implementations • 29 Sep 2021 • Yonggan Fu, Qixuan Yu, Meng Li, Xu Ouyang, Vikas Chandra, Yingyan Lin
Contrastive learning, which learns visual representations by enforcing feature consistency under different augmented views, has emerged as one of the most effective unsupervised learning methods.
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
no code implementations • 16 Jun 2021 • Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh, Ozlem Kalinli, Michael L. Seltzer, Vikas Chandra
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets.
1 code implementation • 26 Apr 2021 • Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, Qiang Liu
To alleviate this problem, in this work, we introduce novel loss functions in vision transformer training to explicitly encourage diversity across patch representations for more discriminative feature extraction.
Ranked #20 on Semantic Segmentation on Cityscapes val
1 code implementation • 2 Mar 2021 • Kartik Hegde, Po-An Tsai, Sitao Huang, Vikas Chandra, Angshuman Parashar, Christopher W. Fletcher
The key idea is to derive a smooth, differentiable approximation to the otherwise non-smooth, non-convex search space.
no code implementations • 2 Mar 2021 • Lucas D. Young, Fitsum A. Reda, Rakesh Ranjan, Jon Morton, Jun Hu, Yazhu Ling, Xiaoyu Xiang, David Liu, Vikas Chandra
(2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss.
no code implementations • 23 Feb 2021 • Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra
Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices.
2 code implementations • 16 Feb 2021 • Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra
Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks.
Ranked #12 on Neural Architecture Search on ImageNet
1 code implementation • ICLR 2021 • Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin
In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training.
no code implementations • 3 Dec 2020 • Sachin Mehta, Amit Kumar, Fitsum Reda, Varun Nasery, Vikram Mulukutla, Rakesh Ranjan, Vikas Chandra
Video transmission applications (e. g., conferencing) are gaining momentum, especially in times of global health pandemic.
no code implementations • 30 Nov 2020 • Hsin-Pai Cheng, Feng Liang, Meng Li, Bowen Cheng, Feng Yan, Hai Li, Vikas Chandra, Yiran Chen
We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation.
Ranked #5 on Multi-Person Pose Estimation on COCO test-dev
no code implementations • 25 Nov 2020 • Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh, Yongyi Lu, Yuyin Zhou, Qihang Yu, Vikas Chandra, Alan Yuille
To this end, we present Temporal-aware Contrastive self-supervised learningTaCo, as a general paradigm to enhance video CSL.
1 code implementation • CVPR 2021 • Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, Qiang Liu
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems.
2 code implementations • CVPR 2021 • Dilin Wang, Meng Li, Chengyue Gong, Vikas Chandra
Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77. 3% to 80. 7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks.
Ranked #21 on Neural Architecture Search on ImageNet
no code implementations • 28 Oct 2020 • Yongan Zhang, Yonggan Fu, Weiwen Jiang, Chaojian Li, Haoran You, Meng Li, Vikas Chandra, Yingyan Lin
Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered intelligence into numerous applications.
no code implementations • 22 Aug 2020 • Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra, Diana Marculescu
Weight quantization for deep ConvNets has shown promising results for applications such as image classification and semantic segmentation and is especially important for applications where memory storage is limited.
no code implementations • 8 Jul 2020 • Hsin-Pai Cheng, Tunhou Zhang, Yixing Zhang, Shi-Yu Li, Feng Liang, Feng Yan, Meng Li, Vikas Chandra, Hai Li, Yiran Chen
To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method.
no code implementations • 13 Feb 2020 • Meng Li, Yilei Li, Pierce Chuang, Liangzhen Lai, Vikas Chandra
Neural network accelerator is a key enabler for the on-device AI inference, for which energy efficiency is an important metric.
no code implementations • 10 Feb 2020 • Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi
Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).
1 code implementation • ICLR 2020 • Dilin Wang, Meng Li, Lemeng Wu, Vikas Chandra, Qiang Liu
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited.
no code implementations • 25 Sep 2019 • Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra, Diana Marculescu
Weight Quantization for deep convolutional neural networks (CNNs) has shown promising results in compressing and accelerating CNN-powered applications such as semantic segmentation, gesture recognition, and scene understanding.
no code implementations • 13 Sep 2019 • Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra
The results suggest that HDA is an alternative class of Pareto-optimal accelerators to RDA with strength in energy, which can be a better choice than RDAs depending on the use cases.
Distributed, Parallel, and Cluster Computing
2 code implementations • 2 Jun 2018 • Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, Vikas Chandra
Experiments show that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.
1 code implementation • 19 Jan 2018 • Liangzhen Lai, Naveen Suda, Vikas Chandra
Deep Neural Networks are becoming increasingly popular in always-on IoT edge devices performing data analytics right at the source, reducing latency as well as energy consumption for data communication.
no code implementations • 12 Jan 2018 • Liangzhen Lai, Naveen Suda, Vikas Chandra
Efficient and compact neural network models are essential for enabling the deployment on mobile and embedded devices.
no code implementations • 5 Dec 2017 • Hardik Sharma, Jongse Park, Naveen Suda, Liangzhen Lai, Benson Chau, Joon Kyung Kim, Vikas Chandra, Hadi Esmaeilzadeh
Compared to Stripes, BitFusion provides 2. 6x speedup and 3. 9x energy reduction at 45 nm node when BitFusion area and frequency are set to those of Stripes.
18 code implementations • 20 Nov 2017 • Yundong Zhang, Naveen Suda, Liangzhen Lai, Vikas Chandra
We train various neural network architectures for keyword spotting published in literature to compare their accuracy and memory/compute requirements.
Ranked #13 on Keyword Spotting on Google Speech Commands
no code implementations • ICLR 2018 • Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Z. Pan
Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints.
no code implementations • 8 Mar 2017 • Liangzhen Lai, Naveen Suda, Vikas Chandra
To alleviate these problems to some extent, prior research utilize low precision fixed-point numbers to represent the CNN weights and activations.