1 code implementation • 22 Mar 2023 • Shuo Yang, Zhaopan Xu, Kai Wang, Yang You, Hongxun Yao, Tongliang Liu, Min Xu
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space.
no code implementations • 13 Mar 2023 • Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, Jian Zhao
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance.
1 code implementation • 12 Mar 2023 • Zangwei Zheng, Mingyuan Ma, Kai Wang, Ziheng Qin, Xiangyu Yue, Yang You
To address this challenge, we propose a novel method ZSCL to prevent zero-shot transfer degradation in the continual learning of vision-language models in both feature and parameter space.
2 code implementations • 8 Mar 2023 • Kai Wang, Jianyang Gu, Daquan Zhou, Zheng Zhu, Wei Jiang, Yang You
To the best of our knowledge, we are the first to achieve higher accuracy on complex architectures than simple ones, such as 75. 1\% with ResNet-18 and 72. 6\% with ConvNet-3 on ten images per class of CIFAR-10.
1 code implementation • 8 Mar 2023 • Ziheng Qin, Kai Wang, Zangwei Zheng, Jianyang Gu, Xiangyu Peng, Daquan Zhou, Yang You
We train the full data in the last few epochs to improve the performance of our method, which further reduces the bias of the total update.
1 code implementation • 6 Mar 2023 • Yujing Lou, Zelin Ye, Yang You, Nianjuan Jiang, Jiangbo Lu, Weiming Wang, Lizhuang Ma, Cewu Lu
CRIN directly takes the coordinates of points as input and transforms local points into rotation-invariant representations via centrifugal reference frames.
2 code implementations • 28 Feb 2023 • Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Wei Jiang, Yang You
Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.
no code implementations • 27 Feb 2023 • Yang You, Vincent Thomas, Francis Colas, Rachid Alami, Olivier Buffet
Based on this, we propose two contributions: 1) an approach to automatically generate an uncertain human behavior (a policy) for each given objective function while accounting for possible robot behaviors; and 2) a robot planning algorithm that is robust to the above-mentioned uncertainties and relies on solving a partially observable Markov decision process (POMDP) obtained by reasoning on a distribution over human behaviors.
1 code implementation • 6 Feb 2023 • Yuliang Liu, Shenggui Li, Jiarui Fang, Yanjun Shao, Boyuan Yao, Yang You
To address these challenges, we introduce a system that can jointly optimize distributed execution and gradient checkpointing plans.
1 code implementation • 30 Jan 2023 • Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab, Neil Houlsby, Mostafa Dehghani, Yang You
However, most standard neural networks have the same function type and fixed computation budget on different samples regardless of their nature and difficulty.
1 code implementation • 1 Jan 2023 • Huaizheng Zhang, Yuanming Li, Wencong Xiao, Yizheng Huang, Xing Di, Jianxiong Yin, Simon See, Yong Luo, Chiew Tong Lau, Yang You
The vision of this paper is to provide a more comprehensive and practical benchmark study for MIG in order to eliminate the need for tedious manual benchmarking and tuning efforts.
1 code implementation • 30 Dec 2022 • Tom Young, Yang You
We empirically quantify such inconsistencies in the simple scenario of bigrams for two common styles of masked language models: T5-style and BERT-style.
no code implementations • 29 Dec 2022 • Xin Hu, Lingling Zhang, Jun Liu, Jinfu Fan, Yang You, Yaqiang Wu
These lead to the fact that traditional data-driven detection model is not suitable for diagrams.
no code implementations • 10 Dec 2022 • Haichen Huang, Jiarui Fang, Hongxin Liu, Shenggui Li, Yang You
People who are inaccessible to a large number of GPUs resort to heterogeneous training systems for storing model parameters in CPU memory.
1 code implementation • 24 Nov 2022 • Yang You, Zhuochen Miao, Kai Xiong, Weiming Wang, Cewu Lu
In contrast, our proposed OneLoc algorithm efficiently finds the object center and bounding box size by a special voting scheme.
1 code implementation • 24 Nov 2022 • Yang You, Wenhao He, Michael Xu Liu, Weiming Wang, Cewu Lu
In this paper, we propose a novel method for sim-to-real pose estimation, which is effective on both instance-level and category-level settings.
1 code implementation • 26 Oct 2022 • Chenhui Shen, Liying Cheng, Lidong Bing, Yang You, Luo Si
A wide range of control perspectives have been explored in controllable text generation.
no code implementations • 6 Sep 2022 • Jiangsu Du, Ziming Liu, Jiarui Fang, Shenggui Li, Yongbin Li, Yutong Lu, Yang You
Although the AI community has expanded the model scale to the trillion parameter level, the practical deployment of 10-100 billion parameter models is still uncertain due to the latency, throughput, and memory constraints.
no code implementations • 18 Aug 2022 • Zangwei Zheng, Xiangyu Yue, Kai Wang, Yang You
In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction.
1 code implementation • 8 Aug 2022 • Jiarui Fang, Geng Zhang, Jiatong Han, Shenggui Li, Zhengda Bian, Yongbin Li, Jin Liu, Yang You
Deep learning recommendation models (DLRMs) have been widely applied in Internet companies.
2 code implementations • 19 Jul 2022 • Yizheng Huang, Huaizheng Zhang, Yuanming Li, Chiew Tong Lau, Yang You
In data-centric AI, active learning (AL) plays a vital role, but current AL tools 1) require users to manually select AL strategies, and 2) can not perform AL tasks efficiently.
1 code implementation • 28 May 2022 • Jianfei Yang, Xiangyu Peng, Kai Wang, Zheng Zhu, Jiashi Feng, Lihua Xie, Yang You
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain.
1 code implementation • 23 May 2022 • Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Jiankang Deng, Xinchao Wang, Hakan Bilen, Yang You
Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE.
no code implementations • 21 May 2022 • Fuzhao Xue, Jianghai Chen, Aixin Sun, Xiaozhe Ren, Zangwei Zheng, Xiaoxin He, Xin Jiang, Yang You
In this paper, we revisit these conventional configurations.
Ranked #88 on Image Classification on ImageNet
1 code implementation • 30 Apr 2022 • Kai Wang, Xiangyu Peng, Shuo Yang, Jianfei Yang, Zheng Zhu, Xinchao Wang, Yang You
This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well.
1 code implementation • 13 Apr 2022 • Zangwei Zheng, Pengtai Xu, Xuan Zou, Da Tang, Zhen Li, Chenguang Xi, Peng Wu, Leqi Zou, Yijie Zhu, Ming Chen, Xiangzhuo Ding, Fuzhao Xue, Ziheng Qin, Youlong Cheng, Yang You
Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks.
1 code implementation • CVPR 2022 • Wangbo Zhao, Kai Wang, Xiangxiang Chu, Fuzhao Xue, Xinchao Wang, Yang You
Text-based video segmentation aims to segment the target object in a video based on a describing sentence.
Ranked #7 on Referring Expression Segmentation on A2D Sentences
Optical Flow Estimation Referring Expression Segmentation +2
1 code implementation • CVPR 2022 • Yang You, Ruoxi Shi, Weiming Wang, Cewu Lu
Drawing inspirations from traditional point pair features (PPFs), in this paper, we design a novel Category-level PPF (CPPF) voting method to achieve accurate, robust and generalizable 9D pose estimation in the wild.
Ranked #1 on 6D Pose Estimation using RGBD on REAL275 (mAP 15, 5cm metric)
1 code implementation • CVPR 2022 • Yong liu, Siqi Mai, Xiangning Chen, Cho-Jui Hsieh, Yang You
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers.
2 code implementations • CVPR 2022 • Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang, Shuo Wang, Guan Huang, Hakan Bilen, Xinchao Wang, Yang You
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one.
1 code implementation • 2 Mar 2022 • Shenggan Cheng, Xuanlei Zhao, Guangyang Lu, Jiarui Fang, Zhongming Yu, Tian Zheng, Ruidong Wu, Xiwen Zhang, Jian Peng, Yang You
In this work, we present FastFold, an efficient implementation of AlphaFold for both training and inference.
1 code implementation • 24 Feb 2022 • Jie Zhu, Shenggui Li, Yang You
In this paper, we proposed Sky Computing, a load-balanced model parallelism framework to adaptively allocate the weights to devices.
1 code implementation • CVPR 2022 • Xiangyu Peng, Kai Wang, Zheng Zhu, Mang Wang, Yang You
For high performance Siamese representation learning, one of the keys is to design good contrastive pairs.
no code implementations • 26 Jan 2022 • Fuzhao Xue, Xiaoxin He, Xiaozhe Ren, Yuxuan Lou, Yang You
Mixture-of-experts (MoE) is a powerful sparse architecture including multiple experts.
no code implementations • 21 Nov 2021 • Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu
Pixel-level 2D object semantic understanding is an important topic in computer vision and could help machine deeply understand objects (e. g. functionality and affordance) in our daily life.
no code implementations • 1 Nov 2021 • Xiaoxin He, Fuzhao Xue, Xiaozhe Ren, Yang You
Deep learning have achieved promising results on a wide spectrum of AI applications.
1 code implementation • 28 Oct 2021 • Shenggui Li, Jiarui Fang, Zhengda Bian, Hongxin Liu, Yuliang Liu, Haichen Huang, Boxiang Wang, Yang You
The success of Transformer models has pushed the deep learning model scale to billions of parameters.
1 code implementation • Findings (ACL) 2022 • Chenhui Shen, Liying Cheng, Ran Zhou, Lidong Bing, Yang You, Luo Si
A more useful text generator should leverage both the input text and the control signal to guide the generation, which can only be built with a deep understanding of the domain knowledge.
no code implementations • 29 Sep 2021 • Yong liu, Siqi Mai, Xiangning Chen, Cho-Jui Hsieh, Yang You
Large-batch training is an important direction for distributed machine learning, which can improve the utilization of large-scale clusters and therefore accelerate the training process.
no code implementations • 17 Sep 2021 • Yang You, Vincent Thomas, Francis Colas, Olivier Buffet
This paper looks at solving collaborative planning problems formalized as Decentralized POMDPs (Dec-POMDPs) by searching for Nash equilibria, i. e., situations where each agent's policy is a best response to the other agents' (fixed) policies.
no code implementations • 5 Sep 2021 • Yuxuan Lou, Fuzhao Xue, Zangwei Zheng, Yang You
Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i. e. feed-forward network) of transformer.
1 code implementation • 12 Aug 2021 • Jiarui Fang, Zilin Zhu, Shenggui Li, Hui Su, Yang Yu, Jie zhou, Yang You
PatrickStar uses the CPU-GPU heterogeneous memory space to store the model data.
no code implementations • 8 Aug 2021 • Zhengda Bian, Shenggui Li, Wei Wang, Yang You
ONES automatically manages the elasticity of each job based on the training batch size, so as to maximize GPU utilization and improve scheduling efficiency.
1 code implementation • 25 Jul 2021 • Fuzhao Xue, Ziji Shi, Futao Wei, Yuxuan Lou, Yong liu, Yang You
To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or model compressing along with the depth.
Ranked #577 on Image Classification on ImageNet
no code implementations • ICLR 2022 • Yong liu, Xiangning Chen, Minhao Cheng, Cho-Jui Hsieh, Yang You
Current methods usually use extensive data augmentation to increase the batch size, but we found the performance gain with data augmentation decreases as batch size increases, and data augmentation will become insufficient after certain point.
no code implementations • 30 May 2021 • Zhengda Bian, Qifan Xu, Boxiang Wang, Yang You
Our work is the first to introduce a 3-dimensional model parallelism for expediting huge language models.
no code implementations • 30 May 2021 • Boxiang Wang, Qifan Xu, Zhengda Bian, Yang You
It increases efficiency by reducing communication overhead and lowers the memory required for each GPU.
no code implementations • 26 May 2021 • Shenggui Li, Fuzhao Xue, Chaitanya Baranwal, Yongbin Li, Yang You
That is, with sparse attention, our sequence parallelism enables us to train transformer with infinite long sequence.
1 code implementation • CVPR 2022 • Kai Wang, Shuo Wang, Panpan Zhang, Zhipeng Zhou, Zheng Zhu, Xiaobo Wang, Xiaojiang Peng, Baigui Sun, Hao Li, Yang You
This method adopts Dynamic Class Pool (DCP) for storing and updating the identities features dynamically, which could be regarded as a substitute for the FC layer.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
1 code implementation • 12 Apr 2021 • Qifan Xu, Shenggui Li, Chaoyu Gong, Yang You
However, due to memory constraints, model parallelism must be utilized to host large models that would otherwise not fit into the memory of a single device.
1 code implementation • CVPR 2021 • Ruoxi Shi, Zhengrong Xue, Yang You, Cewu Lu
In this paper, we propose an unsupervised aligned keypoint detector, Skeleton Merger, which utilizes skeletons to reconstruct objects.
2 code implementations • 24 Feb 2021 • Yang You, Yujing Lou, Ruoxi Shi, Qi Liu, Yu-Wing Tai, Lizhuang Ma, Weiming Wang, Cewu Lu
Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point.
1 code implementation • CVPR 2022 • Yang You, Zelin Ye, Yujing Lou, Chengkun Li, Yong-Lu Li, Lizhuang Ma, Weiming Wang, Cewu Lu
In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations.
1 code implementation • CVPR 2022 • Yang You, Wenhai Liu, Yanjie Ze, Yong-Lu Li, Weiming Wang, Cewu Lu
Keypoint detection is an essential component for the object registration and alignment.
no code implementations • 30 Oct 2020 • Arissa Wongpanich, Hieu Pham, James Demmel, Mingxing Tan, Quoc Le, Yang You, Sameer Kumar
EfficientNets are a family of state-of-the-art image classification models based on efficiently scaled convolutional neural networks.
no code implementations • 19 Oct 2020 • Yuanhao Xiong, Xuanqing Liu, Li-Cheng Lan, Yang You, Si Si, Cho-Jui Hsieh
For end-to-end efficiency, unlike previous work that assumes random hyperparameter tuning, which over-emphasizes the tuning time, we propose to evaluate with a bandit hyperparameter tuning strategy.
no code implementations • 18 Sep 2020 • Le Xiao, Xiaoting Li, Datao Gong, Jinghong Chen, Di Guo, Huiqin He, Suen Hou, Guangming Huang, Chonghan Liu, Tiankuan Liu, Xiangming Sun, Ping-Kun Teng, Bozorgmehr Vosooghi, Annie C. Xiang, Jingbo Ye, Yang You, Zhiheng Zuo
In this paper, we present the design and test results of LOCx2, a transmitter ASIC for the ATLAS Liquid Argon Calorimeter trigger upgrade.
Instrumentation and Detectors
no code implementations • 15 Jun 2020 • Yang You, Yuhui Wang, huan zhang, Zhao Zhang, James Demmel, Cho-Jui Hsieh
For the first time we scale the batch size on ImageNet to at least a magnitude larger than all previous work, and provide detailed studies on the performance of many state-of-the-art optimization schemes under this setting.
1 code implementation • 20 Apr 2020 • Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Lizhuang Ma, Cewu Lu, Weiming Wang
Visual semantic correspondence is an important topic in computer vision and could help machine understand objects in our daily life.
1 code implementation • CVPR 2020 • Yang You, Yujing Lou, Chengkun Li, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu
Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision.
1 code implementation • ECCV 2020 • Yujing Lou, Yang You, Chengkun Li, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu
Semantic understanding of 3D objects is crucial in many applications such as object manipulation.
1 code implementation • 20 Nov 2019 • Ruobing Han, James Demmel, Yang You
Our experimental results show that for many applications, APS can train state-of-the-art models by 8-bit gradients with no or only a tiny accuracy loss (<0. 05%).
23 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)
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.
1 code implementation • 24 Jan 2019 • Yang You, Liangwei Li, Baisong Guo, Weiming Wang, Cewu Lu
Deep reinforcement learning (DRL) has gained a lot of attention in recent years, and has been proven to be able to play Atari games and Go at or above human levels.
1 code implementation • 23 Nov 2018 • Yang You, Yujing Lou, Qi Liu, Yu-Wing Tai, Lizhuang Ma, Cewu Lu, Weiming Wang
Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown.
no code implementations • ICLR 2018 • Boris Ginsburg, Igor Gitman, Yang You
Using LARS, we scaled AlexNet and ResNet-50 to a batch size of 16K.
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.
10 code implementations • 13 Aug 2017 • Yang You, Igor Gitman, Boris Ginsburg
Using LARS, we scaled Alexnet up to a batch size of 8K, and Resnet-50 to a batch size of 32K without loss in accuracy.
no code implementations • NeurIPS 2016 • Yang You, Xiangru Lian, Ji Liu, Hsiang-Fu Yu, Inderjit S. Dhillon, James Demmel, Cho-Jui Hsieh
n this paper, we propose and study an Asynchronous parallel Greedy Coordinate Descent (Asy-GCD) algorithm for minimizing a smooth function with bounded constraints.