no code implementations • 7 May 2023 • Zhanpeng Zeng, Cole Hawkins, Mingyi Hong, Aston Zhang, Nikolaos Pappas, Vikas Singh, Shuai Zheng
Transformers are central in modern natural language processing and computer vision applications.
1 code implementation • 10 Apr 2023 • Shuhuai Ren, Aston Zhang, Yi Zhu, Shuai Zhang, Shuai Zheng, Mu Li, Alex Smola, Xu sun
This work proposes POMP, a prompt pre-training method for vision-language models.
Ranked #1 on Open Vocabulary Semantic Segmentation on PascalVOC-20 (hIoU metric)
1 code implementation • CVPR 2023 • Zhijie Shen, Zishuo Zheng, Chunyu Lin, Lang Nie, Kang Liao, Shuai Zheng, Yao Zhao
Based on the Manhattan World assumption, most existing indoor layout estimation schemes focus on recovering layouts from vertically compressed 1D sequences.
no code implementations • 16 Feb 2023 • Hongzheng Chen, Cody Hao Yu, Shuai Zheng, Zhen Zhang, Zhiru Zhang, Yida Wang
Specifically, the schedule works on a PyTorch model and uses a set of schedule primitives to convert the model for common model training optimizations such as high-performance kernels, effective 3D parallelism, and efficient activation checkpointing.
no code implementations • 21 Dec 2022 • M Saiful Bari, Aston Zhang, Shuai Zheng, Xingjian Shi, Yi Zhu, Shafiq Joty, Mu Li
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way.
no code implementations • 10 Dec 2022 • Chaoyang He, Shuai Zheng, Aston Zhang, George Karypis, Trishul Chilimbi, Mahdi Soltanolkotabi, Salman Avestimehr
The mixture of Expert (MoE) parallelism is a recent advancement that scales up the model size with constant computational cost.
no code implementations • 7 Dec 2022 • Shuai Zheng
Graph neural networks (GNNs) have shown remarkable performance on homophilic graph data while being far less impressive when handling non-homophilic graph data due to the inherent low-pass filtering property of GNNs.
1 code implementation • 19 Sep 2022 • Zongyu Li, Zhenfeng Zhu, Xiao bo Guo, Shuai Zheng, Zhenyu Guo, Siwei Qiang, Yao Zhao
The concept of causality plays a significant role in human cognition.
1 code implementation • 4 Jul 2022 • Haotao Wang, Aston Zhang, Shuai Zheng, Xingjian Shi, Mu Li, Zhangyang Wang
In addition, NoFrost achieves a $23. 56\%$ adversarial robustness against PGD attack, which improves the $13. 57\%$ robustness in BN-based AT.
1 code implementation • 4 Jul 2022 • Haotao Wang, Aston Zhang, Yi Zhu, Shuai Zheng, Mu Li, Alex Smola, Zhangyang Wang
However, in real-world applications, it is common for the training sets to have long-tailed distributions.
no code implementations • 15 Jun 2022 • Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas, Davide Bernardi, Abhishek Bhagia, Claudio Delli Bovi, Jin Cao, Rakesh Chada, Amit Chauhan, Luoxin Chen, Anurag Dwarakanath, Satyam Dwivedi, Turan Gojayev, Karthik Gopalakrishnan, Thomas Gueudre, Dilek Hakkani-Tur, Wael Hamza, Jonathan Hueser, Kevin Martin Jose, Haidar Khan, Beiye Liu, Jianhua Lu, Alessandro Manzotti, Pradeep Natarajan, Karolina Owczarzak, Gokmen Oz, Enrico Palumbo, Charith Peris, Chandana Satya Prakash, Stephen Rawls, Andy Rosenbaum, Anjali Shenoy, Saleh Soltan, Mukund Harakere Sridhar, Liz Tan, Fabian Triefenbach, Pan Wei, Haiyang Yu, Shuai Zheng, Gokhan Tur, Prem Natarajan
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference intent-classification +5
1 code implementation • 11 Mar 2022 • Shuai Zheng, Zhenfeng Zhu, Zhizhe Liu, Zhenyu Guo, Yang Liu, Yuchen Yang, Yao Zhao
For disease prediction tasks, most existing graph-based methods tend to define the graph manually based on specified modality (e. g., demographic information), and then integrated other modalities to obtain the patient representation by Graph Representation Learning (GRL).
no code implementations • 29 Sep 2021 • Bingcong Li, Shuai Zheng, Parameswaran Raman, Anshumali Shrivastava, Georgios B. Giannakis
On-device memory concerns in distributed deep learning are becoming more severe due to i) the growth of model size in multi-GPU training, and ii) the adoption of neural networks for federated learning on IoT devices with limited storage.
1 code implementation • 24 Sep 2021 • Johnathan Xie, Shuai Zheng
Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks.
no code implementations • 19 Jul 2021 • Zhenyu Guo, Shuai Zheng, Zhizhe Liu, Kun Yan, Zhenfeng Zhu
Treatment effect estimation, which refers to the estimation of causal effects and aims to measure the strength of the causal relationship, is of great importance in many fields but is a challenging problem in practice.
no code implementations • 1 Jul 2021 • Shuai Zheng, Zhenfeng Zhu, Zhizhe Liu, Zhenyu Guo, Yang Liu, Yao Zhao
However, it is not easy for these approaches to generalize to unseen samples.
1 code implementation • 17 May 2021 • Yuchen Zhong, Cong Xie, Shuai Zheng, Haibin Lin
Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training.
no code implementations • 16 Mar 2021 • Qiyao Wang, Ahmed Farahat, Chetan Gupta, Shuai Zheng
Time series data have grown at an explosive rate in numerous domains and have stimulated a surge of time series modeling research.
1 code implementation • 15 Mar 2021 • Zhizhe Liu, Zhenfeng Zhu, Shuai Zheng, Yang Liu, Jiayu Zhou, Yao Zhao
To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning.
no code implementations • 12 Mar 2021 • Shuai Zheng
For real-world graph data, the complex relationship between nodes is often represented as a hard binary link.
no code implementations • 17 Oct 2020 • Yunchao Wei, Shuai Zheng, Ming-Ming Cheng, Hang Zhao, LiWei Wang, Errui Ding, Yi Yang, Antonio Torralba, Ting Liu, Guolei Sun, Wenguan Wang, Luc van Gool, Wonho Bae, Junhyug Noh, Jinhwan Seo, Gunhee Kim, Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang, Chuangchuang Tan, Tao Ruan, Guanghua Gu, Shikui Wei, Yao Zhao, Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych, Zhendong Wang, Zhenyuan Chen, Chen Gong, Huanqing Yan, Jun He
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
no code implementations • 2 Oct 2020 • Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng
There have been numerous methods proposed for human identification, such as face identification, person re-identification, and gait identification.
no code implementations • 24 Aug 2020 • Chi Zhang, Philip Odonkor, Shuai Zheng, Hamed Khorasgani, Susumu Serita, Chetan Gupta
In this paper, we propose a novel Deep Reinforcement Learning approach to solve the dynamic dispatching problem in mining.
no code implementations • NeurIPS 2020 • Cong Xie, Shuai Zheng, Oluwasanmi Koyejo, Indranil Gupta, Mu Li, Haibin Lin
The scalability of Distributed Stochastic Gradient Descent (SGD) is today limited by communication bottlenecks.
1 code implementation • 24 Jun 2020 • Shuai Zheng, Haibin Lin, Sheng Zha, Mu Li
Using the proposed LANS method and the learning rate scheme, we scaled up the mini-batch sizes to 96K and 33K in phases 1 and 2 of BERT pretraining, respectively.
1 code implementation • CVPR 2020 • Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang, Zhizhe Liu, Jian Cheng, Yao Zhao
Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks.
no code implementations • 22 Oct 2019 • Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng
The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors.
no code implementations • 4 Oct 2019 • Shuai Zheng, Chetan Gupta, Susumu Serita
To address this, we enhance our deep RL model with an approach for dispatching policy transfer.
no code implementations • 4 Oct 2019 • Shuai Zheng, Ahmed Farahat, Chetan Gupta
GAN-FP first utilizes two GAN networks to simultaneously generate training samples and build an inference network that can be used to predict failures for new samples.
no code implementations • 11 Jul 2019 • Shuai Zheng, Zhenfeng Zhu, Jian Cheng, Yandong Guo, Yao Zhao
Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation.
4 code implementations • 9 Jul 2019 • Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng, Yi Zhu
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
1 code implementation • NeurIPS 2019 • Shuai Zheng, Ziyue Huang, James T. Kwok
In particular, on distributed ResNet training with 7 workers on the ImageNet, the proposed algorithm achieves the same testing accuracy as momentum SGD using full-precision gradients, but with $46\%$ less wall clock time.
no code implementations • 23 May 2019 • Shuai Zheng, James T. Kwok
Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks.
no code implementations • 12 Apr 2019 • Qiyao Wang, Shuai Zheng, Ahmed Farahat, Susumu Serita, Chetan Gupta
In this work, we propose a novel Functional Data Analysis (FDA) method called functional Multilayer Perceptron (functional MLP) for RUL estimation.
no code implementations • 24 Sep 2018 • Bryan A. Plummer, M. Hadi Kiapour, Shuai Zheng, Robinson Piramuthu
In this paper, we introduce an attribute-based interactive image search which can leverage human-in-the-loop feedback to iteratively refine image search results.
2 code implementations • 3 Jul 2018 • Shuai Zheng, Fan Yang, M. Hadi Kiapour, Robinson Piramuthu
Understanding clothes from a single image has strong commercial and cultural impacts on modern societies.
no code implementations • ICML 2018 • Shuai Zheng, James T. Kwok
The memory cost of SSAG does not depend on the sample size, while that of S-SAGA is the same as those of variance reduction methods on un- perturbed data.
no code implementations • 13 Apr 2018 • Shuai Zheng, Chris Ding, Feiping Nie
Singular value decomposition (SVD) is the mathematical basis of principal component analysis (PCA).
no code implementations • 6 Apr 2018 • Shuai Zheng, Chris Ding
Support Vector Machine (SVM) is an efficient classification approach, which finds a hyperplane to separate data from different classes.
1 code implementation • CVPR 2018 • Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang
To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map.
1 code implementation • ECCV 2018 • Bryan A. Plummer, Paige Kordas, M. Hadi Kiapour, Shuai Zheng, Robinson Piramuthu, Svetlana Lazebnik
This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model.
no code implementations • ICML 2017 • Shuai Zheng, James T. Kwok
Deep networks are highly nonlinear and difficult to optimize.
2 code implementations • 21 Mar 2017 • Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang
Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information.
Conditional Image Generation Vocal Bursts Intensity Prediction
no code implementations • 24 Jan 2017 • Måns Larsson, Anurag Arnab, Fredrik Kahl, Shuai Zheng, Philip Torr
It is empirically demonstrated that such learned potentials can improve segmentation accuracy and that certain label class interactions are indeed better modelled by a non-Gaussian potential.
no code implementations • 14 Oct 2016 • Shuai Zheng, Chris Ding
The problem is to find a subspace to maximize the alignment between subspace-transformed data kernel and class indicator kernel.
no code implementations • 14 Oct 2016 • Shuai Zheng, Feiping Nie, Chris Ding, Heng Huang
In null space based LDA (NLDA), a well-known LDA extension, between-class distance is maximized in the null space of the within-class scatter matrix.
no code implementations • 14 Oct 2016 • Shuai Zheng, Xiao Cai, Chris Ding, Feiping Nie, Heng Huang
Real life data often includes information from different channels.
1 code implementation • 12 Sep 2016 • James Thewlis, Shuai Zheng, Philip H. S. Torr, Andrea Vedaldi
Deep Matching (DM) is a popular high-quality method for quasi-dense image matching.
no code implementations • 4 May 2016 • Shuai Zheng, Abhinav Vishnu, Chris Ding
Deep Learning is a very powerful machine learning model.
no code implementations • 24 Apr 2016 • Shuai Zheng, James T. Kwok
The alternating direction method of multipliers (ADMM) is a powerful optimization solver in machine learning.
no code implementations • 25 Feb 2016 • Shuai Zheng, Ruiliang Zhang, James T. Kwok
In regularized risk minimization, the associated optimization problem becomes particularly difficult when both the loss and regularizer are nonsmooth.
1 code implementation • 25 Nov 2015 • Anurag Arnab, Sadeep Jayasumana, Shuai Zheng, Philip Torr
Recent deep learning approaches have incorporated CRFs into Convolutional Neural Networks (CNNs), with some even training the CRF end-to-end with the rest of the network.
Ranked #55 on Semantic Segmentation on PASCAL Context
no code implementations • 16 Nov 2015 • Alexander Kirillov, Dmitrij Schlesinger, Shuai Zheng, Bogdan Savchynskyy, Philip H. S. Torr, Carsten Rother
We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters.
no code implementations • 7 Aug 2015 • Ruiliang Zhang, Shuai Zheng, James T. Kwok
With the recent proliferation of large-scale learning problems, there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its variants.
6 code implementations • ICCV 2015 • Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su, Dalong Du, Chang Huang, Philip H. S. Torr
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding.
Ranked #36 on Semantic Segmentation on PASCAL VOC 2012 test
no code implementations • CVPR 2014 • Shuai Zheng, Ming-Ming Cheng, Jonathan Warrell, Paul Sturgess, Vibhav Vineet, Carsten Rother, Philip H. S. Torr
The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e. g. "I see a shiny red chair').
no code implementations • 16 Oct 2013 • Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Jonathan Warrell, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy Mitra, Philip Torr
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.