1 code implementation • EMNLP 2021 • Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael Mahoney
Hidden within a one-layer randomly weighted Transformer, we find that subnetworks that can achieve 29. 45/17. 29 BLEU on IWSLT14/WMT14.
no code implementations • ICML 2020 • Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, Joseph Gonzalez
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference.
1 code implementation • 22 Jun 2022 • Peiyuan Liao, Xiuyu Li, Xihui Liu, Kurt Keutzer
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation.
1 code implementation • 20 Jun 2022 • Tian Li, Xiang Chen, Zhen Dong, Weijiang Yu, Yijun Yan, Kurt Keutzer, Shanghang Zhang
Then during training, DASK injects pivot-related knowledge graph information into source domain texts.
1 code implementation • 2 Jun 2022 • Sehoon Kim, Amir Gholami, Albert Shaw, Nicholas Lee, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Kurt Keutzer
After reexamining the design choices for both the macro and micro-architecture of Conformer, we propose the Squeezeformer model, which consistently outperforms the state-of-the-art ASR models under the same training schemes.
Ranked #26 on
Speech Recognition
on LibriSpeech test-clean
no code implementations • 4 May 2022 • Zhen Dong, Kaicheng Zhou, Guohao Li, Qiang Zhou, Mingfei Guo, Bernard Ghanem, Kurt Keutzer, Shanghang Zhang
Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs).
no code implementations • 3 May 2022 • Jinze Yu, Jiaming Liu, Xiaobao Wei, Haoyi Zhou, Yohei Nakata, Denis Gudovskiy, Tomoyuki Okuno, JianXin Li, Kurt Keutzer, Shanghang Zhang
With these strategies, more accurate pseudo labels can be obtained, and knowledge can be better transferred from source to target, thus improving the cross-domain capability of the detection transformer.
no code implementations • 21 Apr 2022 • Chenfeng Xu, Tian Li, Chen Tang, Lingfeng Sun, Kurt Keutzer, Masayoshi Tomizuka, Alireza Fathi, Wei Zhan
It is hard to replicate these approaches in trajectory forecasting due to the lack of adequate trajectory data (e. g., 34K samples in the nuScenes dataset).
no code implementations • 20 Apr 2022 • Sheng Shen, Chunyuan Li, Xiaowei Hu, Yujia Xie, Jianwei Yang, Pengchuan Zhang, Anna Rohrbach, Zhe Gan, Lijuan Wang, Lu Yuan, Ce Liu, Kurt Keutzer, Trevor Darrell, Jianfeng Gao
In this paper, we propose K-LITE (Knowledge-augmented Language-Image Training and Evaluation), a simple strategy to leverage external knowledge to build transferable visual systems: In training, it enriches entities in natural language with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that can understand both visual concepts and their knowledge; In evaluation, the natural language is also augmented with external knowledge and then used to reference learned visual concepts (or describe new ones) to enable zero-shot and few-shot transfer of the pre-trained models.
1 code implementation • 29 Mar 2022 • Woosuk Kwon, Sehoon Kim, Michael W. Mahoney, Joseph Hassoun, Kurt Keutzer, Amir Gholami
Pruning is an effective way to reduce the huge inference cost of large Transformer models.
1 code implementation • 11 Mar 2022 • Sheng Shen, Pete Walsh, Kurt Keutzer, Jesse Dodge, Matthew Peters, Iz Beltagy
As an alternative, we consider a staged training setup that begins with a small model and incrementally increases the amount of compute used for training by applying a "growth operator" to increase the model depth and width.
1 code implementation • NeurIPS 2021 • Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
We analyze NovelD thoroughly in MiniGrid and found that empirically it helps the agent explore the environment more uniformly with a focus on exploring beyond the boundary.
1 code implementation • 25 Oct 2021 • Ravi Krishna, Aravind Kalaiah, Bichen Wu, Maxim Naumov, Dheevatsa Mudigere, Misha Smelyanskiy, Kurt Keutzer
Neural architecture search (NAS) methods aim to automatically find the optimal deep neural network (DNN) architecture as measured by a given objective function, typically some combination of task accuracy and inference efficiency.
Click-Through Rate Prediction
Natural Language Processing
+1
no code implementations • 25 Sep 2021 • Xiangyu Yue, Zangwei Zheng, Colorado Reed, Hari Prasanna Das, Kurt Keutzer, Alberto Sangiovanni Vincentelli
Multi-source Domain Adaptation (MDA) aims to transfer predictive models from multiple, fully-labeled source domains to an unlabeled target domain.
1 code implementation • 8 Sep 2021 • Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael W. Mahoney
Hidden within a one-layer randomly weighted Transformer, we find that subnetworks that can achieve 29. 45/17. 29 BLEU on IWSLT14/WMT14.
no code implementations • 18 Aug 2021 • Sicheng Zhao, Guoli Jia, Jufeng Yang, Guiguang Ding, Kurt Keutzer
In this tutorial, we discuss several key aspects of multi-modal emotion recognition (MER).
2 code implementations • 13 Jul 2021 • Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer
Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world.
Ranked #5 on
Visual Entailment
on SNLI-VE val
(using extra training data)
no code implementations • 3 Jul 2021 • Zangwei Zheng, Xiangyu Yue, Kurt Keutzer, Alberto Sangiovanni Vincentelli
In this paper, we propose a scene-aware radar learning framework for accurate and robust object detection.
1 code implementation • 2 Jul 2021 • Sehoon Kim, Sheng Shen, David Thorsley, Amir Gholami, Woosuk Kwon, Joseph Hassoun, Kurt Keutzer
We extensively test the performance of LTP on GLUE tasks and show that our method outperforms the prior state-of-the-art token pruning methods by up to ~2. 5% higher accuracy with the same amount of FLOPs.
no code implementations • 30 Jun 2021 • Sicheng Zhao, Xingxu Yao, Jufeng Yang, Guoli Jia, Guiguang Ding, Tat-Seng Chua, Björn W. Schuller, Kurt Keutzer
Images can convey rich semantics and induce various emotions in viewers.
no code implementations • 11 Jun 2021 • Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao
IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.
1 code implementation • 8 Jun 2021 • Chenfeng Xu, Shijia Yang, Tomer Galanti, Bichen Wu, Xiangyu Yue, Bohan Zhai, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka
We discover that we can indeed use the same architecture and pretrained weights of a neural net model to understand both images and point-clouds.
1 code implementation • 30 May 2021 • Zhewei Yao, Xiaoxia Wu, Linjian Ma, Sheng Shen, Kurt Keutzer, Michael W. Mahoney, Yuxiong He
Moreover, in order to reduce hyperparameter tuning, a novel adaptive regularization coefficient is deployed to control the regularization penalty adaptively.
no code implementations • 26 Apr 2021 • Zhen Dong, Yizhao Gao, Qijing Huang, John Wawrzynek, Hayden K. H. So, Kurt Keutzer
Automatic algorithm-hardware co-design for DNN has shown great success in improving the performance of DNNs on FPGAs.
1 code implementation • 31 Mar 2021 • Sehoon Kim, Amir Gholami, Zhewei Yao, Nicholas Lee, Patrick Wang, Aniruddha Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer
End-to-end neural network models achieve improved performance on various automatic speech recognition (ASR) tasks.
1 code implementation • CVPR 2021 • Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli
In this paper, we propose an end-to-end Prototypical Cross-domain Self-Supervised Learning (PCS) framework for Few-shot Unsupervised Domain Adaptation (FUDA).
Ranked #3 on
Semantic Segmentation
on DensePASS
no code implementations • 25 Mar 2021 • Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
Thus, it is not surprising that quantization has emerged recently as an important and very active sub-area of research in the efficient implementation of computations associated with Neural Networks.
1 code implementation • ICCV 2021 • Tete Xiao, Colorado J Reed, Xiaolong Wang, Kurt Keutzer, Trevor Darrell
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation.
1 code implementation • 23 Mar 2021 • Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell
Through experimentation on 16 diverse vision datasets, we show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data.
no code implementations • 10 Mar 2021 • Bernie Wang, Simon Xu, Kurt Keutzer, Yang Gao, Bichen Wu
To address this, we propose a novel self-supervised learning task, which we named Trajectory Contrastive Learning (TCL), to improve meta-training.
1 code implementation • 22 Jan 2021 • Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong, Sehoon Kim, Michael W Mahoney, Kurt Keutzer
To address this problem, we introduce a new Hessian Aware Pruning (HAP) method coupled with a Neural Implant approach that uses second-order sensitivity as a metric for structured pruning.
4 code implementations • 5 Jan 2021 • Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks.
no code implementations • ICCV 2021 • Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Zhicheng Yan, Masayoshi Tomizuka, Joseph E. Gonzalez, Kurt Keutzer, Peter Vajda
A recent trend in computer vision is to replace convolutions with transformers.
no code implementations • ACL 2021 • Sheng Shen, Alexei Baevski, Ari S. Morcos, Kurt Keutzer, Michael Auli, Douwe Kiela
We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated.
3 code implementations • 15 Dec 2020 • Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
In this paper, we analyze the pros and cons of each method and propose the regulated difference of inverse visitation counts as a simple but effective criterion for IR.
1 code implementation • 5 Dec 2020 • Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer
In this paper, we propose a contrastive learning framework for cross-domain sentiment classification.
no code implementations • 30 Nov 2020 • Yixiong Zou, Shanghang Zhang, Guangyao Chen, Yonghong Tian, Kurt Keutzer, José M. F. Moura
In this paper, we target a new problem, Annotation-Efficient Video Recognition, to reduce the requirement of annotations for both large amount of samples and the action location.
no code implementations • 25 Nov 2020 • Sicheng Zhao, Xuanbai Chen, Xiangyu Yue, Chuang Lin, Pengfei Xu, Ravi Krishna, Jufeng Yang, Guiguang Ding, Alberto L. Sangiovanni-Vincentelli, Kurt Keutzer
First, we generate an adapted domain to align the source and target domains on the pixel-level by improving CycleGAN with a multi-scale structured cycle-consistency loss.
no code implementations • 25 Nov 2020 • Bichen Wu, Qing He, Peizhao Zhang, Thilo Koehler, Kurt Keutzer, Peter Vajda
More efficient variants of FBWave can achieve up to 109x fewer MACs while still delivering acceptable audio quality.
1 code implementation • 20 Nov 2020 • Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer
Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values.
1 code implementation • 17 Nov 2020 • Sicheng Zhao, Yang Xiao, Jiang Guo, Xiangyu Yue, Jufeng Yang, Ravi Krishna, Pengfei Xu, Kurt Keutzer
C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features.
1 code implementation • 30 Oct 2020 • Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer
Due to scarcity of labels on the target domain, we introduce mutual information maximization (MIM) apart from CL to exploit the features that best support the final prediction.
2 code implementations • 16 Oct 2020 • Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
no code implementations • CVPR 2021 • Bo Li, Yezhen Wang, Shanghang Zhang, Dongsheng Li, Trevor Darrell, Kurt Keutzer, Han Zhao
First, we provide a finite sample bound for both classification and regression problems under Semi-DA.
1 code implementation • CVPR 2021 • Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer
A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations.
no code implementations • 7 Sep 2020 • Sicheng Zhao, Yezhen Wang, Bo Li, Bichen Wu, Yang Gao, Pengfei Xu, Trevor Darrell, Kurt Keutzer
They require prior knowledge of real-world statistics and ignore the pixel-level dropout noise gap and the spatial feature gap between different domains.
1 code implementation • 1 Sep 2020 • Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
1 code implementation • 22 Aug 2020 • Sicheng Zhao, Yaxian Li, Xingxu Yao, Wei-Zhi Nie, Pengfei Xu, Jufeng Yang, Kurt Keutzer
In this paper, we study end-to-end matching between image and music based on emotions in the continuous valence-arousal (VA) space.
1 code implementation • NeurIPS 2020 • Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney
Using these observations, we show that noise-augmentation on mixup training further increases boundary thickness, thereby combating vulnerability to various forms of adversarial attacks and OOD transforms.
no code implementations • 23 Jun 2020 • Bo Li, Yezhen Wang, Tong Che, Shanghang Zhang, Sicheng Zhao, Pengfei Xu, Wei Zhou, Yoshua Bengio, Kurt Keutzer
In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.
3 code implementations • 12 Jun 2020 • Zhen Dong, Dequan Wang, Qijing Huang, Yizhao Gao, Yaohui Cai, Tian Li, Bichen Wu, Kurt Keutzer, John Wawrzynek
Deploying deep learning models on embedded systems has been challenging due to limited computing resources.
6 code implementations • 5 Jun 2020 • Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Zhicheng Yan, Masayoshi Tomizuka, Joseph Gonzalez, Kurt Keutzer, Peter Vajda
In this work, we challenge this paradigm by (a) representing images as semantic visual tokens and (b) running transformers to densely model token relationships.
4 code implementations • 1 Jun 2020 • Zhewei Yao, Amir Gholami, Sheng Shen, Mustafa Mustafa, Kurt Keutzer, Michael W. Mahoney
We introduce ADAHESSIAN, a second order stochastic optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates of the HESSIAN.
2 code implementations • ECCV 2020 • Chenfeng Xu, Bichen Wu, Zining Wang, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka
Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image.
Ranked #14 on
3D Semantic Segmentation
on SemanticKITTI
1 code implementation • ICML 2020 • Sheng Shen, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
To address this, we propose Power Normalization (PN), a novel normalization scheme that resolves this issue by (i) relaxing zero-mean normalization in BN, (ii) incorporating a running quadratic mean instead of per batch statistics to stabilize fluctuations, and (iii) using an approximate backpropagation for incorporating the running statistics in the forward pass.
no code implementations • 26 Feb 2020 • Sicheng Zhao, Bo Li, Colorado Reed, Pengfei Xu, Kurt Keutzer
Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative.
2 code implementations • 26 Feb 2020 • Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, Joseph E. Gonzalez
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference.
2 code implementations • 19 Feb 2020 • Qijing Huang, Dequan Wang, Yizhao Gao, Yaohui Cai, Zhen Dong, Bichen Wu, Kurt Keutzer, John Wawrzynek
In this work, we first investigate the overhead of the deformable convolution on embedded FPGA SoCs, and then show the accuracy-latency tradeoffs for a set of algorithm modifications including full versus depthwise, fixed-shape, and limited-range.
1 code implementation • 19 Feb 2020 • Sicheng Zhao, Bo Li, Xiangyu Yue, Pengfei Xu, Kurt Keutzer
Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network.
no code implementations • 12 Feb 2020 • Sicheng Zhao, Yunsheng Ma, Yang Gu, Jufeng Yang, Tengfei Xing, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer
Emotion recognition in user-generated videos plays an important role in human-centered computing.
1 code implementation • 16 Jan 2020 • Bohan Zhai, Tianren Gao, Flora Xue, Daniel Rothchild, Bichen Wu, Joseph E. Gonzalez, Kurt Keutzer
Automatic speech synthesis is a challenging task that is becoming increasingly important as edge devices begin to interact with users through speech.
Sound Audio and Speech Processing
3 code implementations • CVPR 2020 • Yaohui Cai, Zhewei Yao, Zhen Dong, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0. 5\% of one epoch training time of ResNet50 on ImageNet).
Ranked #1 on
Data Free Quantization
on CIFAR10
(CIFAR-10 W8A8 Top-1 Accuracy metric)
2 code implementations • 16 Dec 2019 • Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney
To illustrate this, we analyze the effect of residual connections and Batch Normalization layers on the trainability of neural networks.
1 code implementation • NeurIPS 2019 • Tianjun Zhang, Zhewei Yao, Amir Gholami, Joseph E. Gonzalez, Kurt Keutzer, Michael W. Mahoney, George Biros
It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE).
no code implementations • 26 Nov 2019 • Tianyuan Zhang, Bichen Wu, Xin Wang, Joseph Gonzalez, Kurt Keutzer
In this work, we propose a method to improve the model capacity without increasing inference-time complexity.
1 code implementation • 22 Nov 2019 • Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA).
Domain Adaptation
Multi-Source Unsupervised Domain Adaptation
2 code implementations • NeurIPS 2020 • Zhen Dong, Zhewei Yao, Yaohui Cai, Daiyaan Arfeen, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
However, the search space for a mixed-precision quantization is exponential in the number of layers.
1 code implementation • NeurIPS 2019 • Sicheng Zhao, Bo Li, Xiangyu Yue, Yang Gu, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer
In this paper, we propose to investigate multi-source domain adaptation for semantic segmentation.
2 code implementations • 7 Oct 2019 • Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, Joseph E. Gonzalez
We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing strategies.
no code implementations • 12 Sep 2019 • Sheng Shen, Zhen Dong, Jiayu Ye, Linjian Ma, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
In particular, we propose a new group-wise quantization scheme, and we use a Hessian based mix-precision method to compress the model further.
1 code implementation • 11 Sep 2019 • Sicheng Zhao, Zizhou Jia, Hui Chen, Leida Li, Guiguang Ding, Kurt Keutzer
By optimizing the PCR loss, PDANet can generate a polarity preserved attention map and thus improve the emotion regression performance.
1 code implementation • ICCV 2019 • Xiangyu Yue, Yang Zhang, Sicheng Zhao, Alberto Sangiovanni-Vincentelli, Kurt Keutzer, Boqing Gong
To this end, we propose a new approach of domain randomization and pyramid consistency to learn a model with high generalizability.
no code implementations • 10 Jun 2019 • Tianjun Zhang, Zhewei Yao, Amir Gholami, Kurt Keutzer, Joseph Gonzalez, George Biros, Michael Mahoney
It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE).
1 code implementation • ICCV 2019 • Zhen Dong, Zhewei Yao, Amir Gholami, Michael Mahoney, Kurt Keutzer
Another challenge is a similar factorial complexity for determining block-wise fine-tuning order when quantizing the model to a target precision.
2 code implementations • 19 Apr 2019 • Bernie Wang, Virginia Wu, Bichen Wu, Kurt Keutzer
2) One-click annotation: Instead of drawing 3D bounding boxes or point-wise labels, we simplify the annotation to just one click on the target object, and automatically generate the bounding box for the target.
22 code implementations • ICLR 2020 • Yang You, Jing Li, Sashank Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, Cho-Jui Hsieh
In this paper, we first study a principled layerwise adaptation strategy to accelerate training of deep neural networks using large mini-batches.
Ranked #11 on
Question Answering
on SQuAD1.1 dev
(F1 metric)
no code implementations • 14 Mar 2019 • Linjian Ma, Gabe Montague, Jiayu Ye, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
In stochastic optimization, using large batch sizes during training can leverage parallel resources to produce faster wall-clock training times per training epoch.
5 code implementations • 27 Feb 2019 • Amir Gholami, Kurt Keutzer, George Biros
ANODE has a memory footprint of O(L) + O(N_t), with the same computational cost as reversing ODE solve.
Clustering Multivariate Time Series
Multivariate Time Series Imputation
1 code implementation • 24 Jan 2019 • Yang You, Jonathan Hseu, Chris Ying, James Demmel, Kurt Keutzer, Cho-Jui Hsieh
LEGW enables Sqrt Scaling scheme to be useful in practice and as a result we achieve much better results than the Linear Scaling learning rate scheme.
2 code implementations • CVPR 2019 • Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael Mahoney
To address this problem, we present a new family of trust region based adversarial attacks, with the goal of computing adversarial perturbations efficiently.
5 code implementations • CVPR 2019 • Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, Kurt Keutzer
Due to this, previous neural architecture search (NAS) methods are computationally expensive.
Ranked #558 on
Image Classification
on ImageNet
no code implementations • 4 Dec 2018 • Norman Mu, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney
We demonstrate the ability of our method to improve language modeling performance by up to 7. 91 perplexity and reduce training iterations by up to $61\%$, in addition to its flexibility in enabling snapshot ensembling and use with adversarial training.
Ranked #48 on
Natural Language Inference
on SNLI
no code implementations • ICLR 2019 • Bichen Wu, Yanghan Wang, Peizhao Zhang, Yuandong Tian, Peter Vajda, Kurt Keutzer
Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices with limited computational and memory resources.
1 code implementation • 21 Nov 2018 • Yifan Yang, Qijing Huang, Bichen Wu, Tianjun Zhang, Liang Ma, Giulio Gambardella, Michaela Blott, Luciano Lavagno, Kees Vissers, John Wawrzynek, Kurt Keutzer
DiracDeltaNet achieves competitive accuracy on ImageNet (88. 7\% top-5), but with 42$\times$ fewer parameters and 48$\times$ fewer OPs than VGG16.
1 code implementation • 5 Nov 2018 • Spyridon Bakas, Mauricio Reyes, Andras Jakab, Stefan Bauer, Markus Rempfler, Alessandro Crimi, Russell Takeshi Shinohara, Christoph Berger, Sung Min Ha, Martin Rozycki, Marcel Prastawa, Esther Alberts, Jana Lipkova, John Freymann, Justin Kirby, Michel Bilello, Hassan Fathallah-Shaykh, Roland Wiest, Jan Kirschke, Benedikt Wiestler, Rivka Colen, Aikaterini Kotrotsou, Pamela Lamontagne, Daniel Marcus, Mikhail Milchenko, Arash Nazeri, Marc-Andre Weber, Abhishek Mahajan, Ujjwal Baid, Elizabeth Gerstner, Dongjin Kwon, Gagan Acharya, Manu Agarwal, Mahbubul Alam, Alberto Albiol, Antonio Albiol, Francisco J. Albiol, Varghese Alex, Nigel Allinson, Pedro H. A. Amorim, Abhijit Amrutkar, Ganesh Anand, Simon Andermatt, Tal Arbel, Pablo Arbelaez, Aaron Avery, Muneeza Azmat, Pranjal B., W Bai, Subhashis Banerjee, Bill Barth, Thomas Batchelder, Kayhan Batmanghelich, Enzo Battistella, Andrew Beers, Mikhail Belyaev, Martin Bendszus, Eze Benson, Jose Bernal, Halandur Nagaraja Bharath, George Biros, Sotirios Bisdas, James Brown, Mariano Cabezas, Shilei Cao, Jorge M. Cardoso, Eric N Carver, Adrià Casamitjana, Laura Silvana Castillo, Marcel Catà, Philippe Cattin, Albert Cerigues, Vinicius S. Chagas, Siddhartha Chandra, Yi-Ju Chang, Shiyu Chang, Ken Chang, Joseph Chazalon, Shengcong Chen, Wei Chen, Jefferson W. Chen, Zhaolin Chen, Kun Cheng, Ahana Roy Choudhury, Roger Chylla, Albert Clérigues, Steven Colleman, Ramiro German Rodriguez Colmeiro, Marc Combalia, Anthony Costa, Xiaomeng Cui, Zhenzhen Dai, Lutao Dai, Laura Alexandra Daza, Eric Deutsch, Changxing Ding, Chao Dong, Shidu Dong, Wojciech Dudzik, Zach Eaton-Rosen, Gary Egan, Guilherme Escudero, Théo Estienne, Richard Everson, Jonathan Fabrizio, Yong Fan, Longwei Fang, Xue Feng, Enzo Ferrante, Lucas Fidon, Martin Fischer, Andrew P. French, Naomi Fridman, Huan Fu, David Fuentes, Yaozong Gao, Evan Gates, David Gering, Amir Gholami, Willi Gierke, Ben Glocker, Mingming Gong, Sandra González-Villá, T. Grosges, Yuanfang Guan, Sheng Guo, Sudeep Gupta, Woo-Sup Han, Il Song Han, Konstantin Harmuth, Huiguang He, Aura Hernández-Sabaté, Evelyn Herrmann, Naveen Himthani, Winston Hsu, Cheyu Hsu, Xiaojun Hu, Xiaobin Hu, Yan Hu, Yifan Hu, Rui Hua, Teng-Yi Huang, Weilin Huang, Sabine Van Huffel, Quan Huo, Vivek HV, Khan M. Iftekharuddin, Fabian Isensee, Mobarakol Islam, Aaron S. Jackson, Sachin R. Jambawalikar, Andrew Jesson, Weijian Jian, Peter Jin, V Jeya Maria Jose, Alain Jungo, B Kainz, Konstantinos Kamnitsas, Po-Yu Kao, Ayush Karnawat, Thomas Kellermeier, Adel Kermi, Kurt Keutzer, Mohamed Tarek Khadir, Mahendra Khened, Philipp Kickingereder, Geena Kim, Nik King, Haley Knapp, Urspeter Knecht, Lisa Kohli, Deren Kong, Xiangmao Kong, Simon Koppers, Avinash Kori, Ganapathy Krishnamurthi, Egor Krivov, Piyush Kumar, Kaisar Kushibar, Dmitrii Lachinov, Tryphon Lambrou, Joon Lee, Chengen Lee, Yuehchou Lee, M Lee, Szidonia Lefkovits, Laszlo Lefkovits, James Levitt, Tengfei Li, Hongwei Li, Hongyang Li, Xiaochuan Li, Yuexiang Li, Heng Li, Zhenye Li, Xiaoyu Li, Zeju Li, Xiaogang Li, Wenqi Li, Zheng-Shen Lin, Fengming Lin, Pietro Lio, Chang Liu, Boqiang Liu, Xiang Liu, Mingyuan Liu, Ju Liu, Luyan Liu, Xavier Llado, Marc Moreno Lopez, Pablo Ribalta Lorenzo, Zhentai Lu, Lin Luo, Zhigang Luo, Jun Ma, Kai Ma, Thomas Mackie, Anant Madabushi, Issam Mahmoudi, Klaus H. Maier-Hein, Pradipta Maji, CP Mammen, Andreas Mang, B. S. Manjunath, Michal Marcinkiewicz, S McDonagh, Stephen McKenna, Richard McKinley, Miriam Mehl, Sachin Mehta, Raghav Mehta, Raphael Meier, Christoph Meinel, Dorit Merhof, Craig Meyer, Robert Miller, Sushmita Mitra, Aliasgar Moiyadi, David Molina-Garcia, Miguel A. B. Monteiro, Grzegorz Mrukwa, Andriy Myronenko, Jakub Nalepa, Thuyen Ngo, Dong Nie, Holly Ning, Chen Niu, Nicholas K Nuechterlein, Eric Oermann, Arlindo Oliveira, Diego D. C. Oliveira, Arnau Oliver, Alexander F. I. Osman, Yu-Nian Ou, Sebastien Ourselin, Nikos Paragios, Moo Sung Park, Brad Paschke, J. Gregory Pauloski, Kamlesh Pawar, Nick Pawlowski, Linmin Pei, Suting Peng, Silvio M. Pereira, Julian Perez-Beteta, Victor M. Perez-Garcia, Simon Pezold, Bao Pham, Ashish Phophalia, Gemma Piella, G. N. Pillai, Marie Piraud, Maxim Pisov, Anmol Popli, Michael P. Pound, Reza Pourreza, Prateek Prasanna, Vesna Prkovska, Tony P. Pridmore, Santi Puch, Élodie Puybareau, Buyue Qian, Xu Qiao, Martin Rajchl, Swapnil Rane, Michael Rebsamen, Hongliang Ren, Xuhua Ren, Karthik Revanuru, Mina Rezaei, Oliver Rippel, Luis Carlos Rivera, Charlotte Robert, Bruce Rosen, Daniel Rueckert, Mohammed Safwan, Mostafa Salem, Joaquim Salvi, Irina Sanchez, Irina Sánchez, Heitor M. Santos, Emmett Sartor, Dawid Schellingerhout, Klaudius Scheufele, Matthew R. Scott, Artur A. Scussel, Sara Sedlar, Juan Pablo Serrano-Rubio, N. Jon Shah, Nameetha Shah, Mazhar Shaikh, B. Uma Shankar, Zeina Shboul, Haipeng Shen, Dinggang Shen, Linlin Shen, Haocheng Shen, Varun Shenoy, Feng Shi, Hyung Eun Shin, Hai Shu, Diana Sima, M Sinclair, Orjan Smedby, James M. Snyder, Mohammadreza Soltaninejad, Guidong Song, Mehul Soni, Jean Stawiaski, Shashank Subramanian, Li Sun, Roger Sun, Jiawei Sun, Kay Sun, Yu Sun, Guoxia Sun, Shuang Sun, Yannick R Suter, Laszlo Szilagyi, Sanjay Talbar, DaCheng Tao, Zhongzhao Teng, Siddhesh Thakur, Meenakshi H Thakur, Sameer Tharakan, Pallavi Tiwari, Guillaume Tochon, Tuan Tran, Yuhsiang M. Tsai, Kuan-Lun Tseng, Tran Anh Tuan, Vadim Turlapov, Nicholas Tustison, Maria Vakalopoulou, Sergi Valverde, Rami Vanguri, Evgeny Vasiliev, Jonathan Ventura, Luis Vera, Tom Vercauteren, C. A. Verrastro, Lasitha Vidyaratne, Veronica Vilaplana, Ajeet Vivekanandan, Qian Wang, Chiatse J. Wang, Wei-Chung Wang, Duo Wang, Ruixuan Wang, Yuanyuan Wang, Chunliang Wang, Guotai Wang, Ning Wen, Xin Wen, Leon Weninger, Wolfgang Wick, Shaocheng Wu, Qiang Wu, Yihong Wu, Yong Xia, Yanwu Xu, Xiaowen Xu, Peiyuan Xu, Tsai-Ling Yang, Xiaoping Yang, Hao-Yu Yang, Junlin Yang, Haojin Yang, Guang Yang, Hongdou Yao, Xujiong Ye, Changchang Yin, Brett Young-Moxon, Jinhua Yu, Xiangyu Yue, Songtao Zhang, Angela Zhang, Kun Zhang, Xue-jie Zhang, Lichi Zhang, Xiaoyue Zhang, Yazhuo Zhang, Lei Zhang, Jian-Guo Zhang, Xiang Zhang, Tianhao Zhang, Sicheng Zhao, Yu Zhao, Xiaomei Zhao, Liang Zhao, Yefeng Zheng, Liming Zhong, Chenhong Zhou, Xiaobing Zhou, Fan Zhou, Hongtu Zhu, Jin Zhu, Ying Zhuge, Weiwei Zong, Jayashree Kalpathy-Cramer, Keyvan Farahani, Christos Davatzikos, Koen van Leemput, Bjoern Menze
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
no code implementations • 11 Oct 2018 • Amir Gholami, Shashank Subramanian, Varun Shenoy, Naveen Himthani, Xiangyu Yue, Sicheng Zhao, Peter Jin, George Biros, Kurt Keutzer
Our biophysics based domain adaptation achieves better results, as compared to the existing state-of-the-art GAN model used to create synthetic data for training.
1 code implementation • ICLR 2019 • Zhewei Yao, Amir Gholami, Daiyaan Arfeen, Richard Liaw, Joseph Gonzalez, Kurt Keutzer, Michael Mahoney
Our method exceeds the performance of existing solutions in terms of both accuracy and the number of SGD iterations (up to 1\% and $5\times$, respectively).
1 code implementation • 22 Sep 2018 • Bichen Wu, Xuanyu Zhou, Sicheng Zhao, Xiangyu Yue, Kurt Keutzer
When training our new model on synthetic data using the proposed domain adaptation pipeline, we nearly double test accuracy on real-world data, from 29. 0% to 57. 4%.
Ranked #23 on
3D Semantic Segmentation
on SemanticKITTI
2 code implementations • 17 May 2018 • Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Kurt Keutzer, Alberto Sangiovanni-Vincentelli, Sanjit A. Seshia
We present a novel framework for augmenting data sets for machine learning based on counterexamples.
no code implementations • 31 Mar 2018 • Xiangyu Yue, Bichen Wu, Sanjit A. Seshia, Kurt Keutzer, Alberto L. Sangiovanni-Vincentelli
The framework supports data collection from both auto-driving scenes and user-configured scenes.
no code implementations • 24 Mar 2018 • Sicheng Zhao, Bichen Wu, Joseph Gonzalez, Sanjit A. Seshia, Kurt Keutzer
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled target domain.
5 code implementations • 23 Mar 2018 • Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter Jin, Sicheng Zhao, Kurt Keutzer
One of the main barriers for deploying neural networks on embedded systems has been large memory and power consumption of existing neural networks.
6 code implementations • NeurIPS 2018 • Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney
Extensive experiments on multiple networks show that saddle-points are not the cause for generalization gap of large batch size training, and the results consistently show that large batch converges to points with noticeably higher Hessian spectrum.
no code implementations • 12 Dec 2017 • Amir Gholami, Ariful Azad, Peter Jin, Kurt Keutzer, Aydin Buluc
We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using minibatch stochastic gradient descent (SGD).
2 code implementations • CVPR 2018 • Bichen Wu, Alvin Wan, Xiangyu Yue, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, Kurt Keutzer
Neural networks rely on convolutions to aggregate spatial information.
1 code implementation • ICML 2018 • Peter Jin, Kurt Keutzer, Sergey Levine
Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels.
6 code implementations • 19 Oct 2017 • Bichen Wu, Alvin Wan, Xiangyu Yue, Kurt Keutzer
In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds.
Ranked #25 on
3D Semantic Segmentation
on SemanticKITTI
no code implementations • 7 Oct 2017 • Forrest Iandola, Kurt Keutzer
Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications.
1 code implementation • 14 Sep 2017 • Yang You, Zhao Zhang, Cho-Jui Hsieh, James Demmel, Kurt Keutzer
If we can make full use of the supercomputer for DNN training, we should be able to finish the 90-epoch ResNet-50 training in one minute.
13 code implementations • 4 Dec 2016 • Bichen Wu, Alvin Wan, Forrest Iandola, Peter H. Jin, Kurt Keutzer
In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment.
no code implementations • 21 Nov 2016 • Matthew W. Moskewicz, Ali Jannesari, Kurt Keutzer
On Qualcomm GPUs, we show that our framework enables productive development of target-specific optimizations, and achieves reasonable absolute performance.
no code implementations • 14 Nov 2016 • Peter H. Jin, Qiaochu Yuan, Forrest Iandola, Kurt Keutzer
Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification and detection in automatic driver assistance systems (ADAS).
no code implementations • 5 Jun 2016 • Khalid Ashraf, Bichen Wu, Forrest N. Iandola, Mattthew W. Moskewicz, Kurt Keutzer
The ability to automatically detect other vehicles on the road is vital to the safety of partially-autonomous and fully-autonomous vehicles.
1 code implementation • 1 Jun 2016 • Matthew Moskewicz, Forrest Iandola, Kurt Keutzer
Results are presented for a case study of targeting the Qualcomm Snapdragon 820 mobile computing platform for CNN deployment.
50 code implementations • 24 Feb 2016 • Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
(2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car.
Ranked #14 on
Network Pruning
on ImageNet
no code implementations • 10 Dec 2015 • Peter H. Jin, Kurt Keutzer
In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts.
no code implementations • CVPR 2016 • Forrest N. Iandola, Khalid Ashraf, Matthew W. Moskewicz, Kurt Keutzer
Therefore, the key consideration here is to reduce communication overhead wherever possible, while not degrading the accuracy of the DNN models that we train.
Ranked #601 on
Image Classification
on ImageNet
no code implementations • 7 Oct 2015 • Forrest N. Iandola, Anting Shen, Peter Gao, Kurt Keutzer
Recently, there has been a flurry of industrial activity around logo recognition, such as Ditto's service for marketers to track their brands in user-generated images, and LogoGrab's mobile app platform for logo recognition.
Ranked #2 on
Object Detection
on FlickrLogos-32
1 code implementation • ITSC 2015 • Forrest Iandola, Matthew Moskewicz, Kurt Keutzer
Histogram of Oriented Gradients (HOG) features are the underlying representation in automotive computer vision applications such as collision avoidance and lane keeping.
1 code implementation • 7 Apr 2014 • Forrest Iandola, Matt Moskewicz, Sergey Karayev, Ross Girshick, Trevor Darrell, Kurt Keutzer
Convolutional Neural Networks (CNNs) can provide accurate object classification.