2.8k citations · 7.4k across the 41 of their papers we have counts for
25 papers · 1 filter
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
Kaichao You, Ximei Wang, Mingsheng Long +1
Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target…
Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
Yong Liu, Chenyu Li, Jianmin Wang +1
Real-world time series are characterized by intrinsic non-stationarity that poses a principal challenge for deep forecasting models. While previous models suffer from complicated s…
SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
Jiaxiang Dong, Haixu Wu, Haoran Zhang +3
Time series analysis is widely used in extensive areas. Recently, to reduce labeling expenses and benefit various tasks, self-supervised pre-training has attracted immense interest…
Solving High-Dimensional PDEs with Latent Spectral Models
Haixu Wu, Tengge Hu, Huakun Luo +2
Deep models have achieved impressive progress in solving partial differential equations (PDEs). A burgeoning paradigm is learning neural operators to approximate the input-output m…
Cycle Self-Training for Domain Adaptation
Hong Liu, Jianmin Wang, Mingsheng Long
Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to narrow the domain shift. Recently, self-training has been gaining momentum…
Self-Tuning for Data-Efficient Deep Learning
Ximei Wang, Jinghan Gao, Mingsheng Long +1
Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive…
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
Kaichao You, Yong Liu, Jianmin Wang +1
This paper studies task adaptive pre-trained model selection, an underexplored problem of assessing pre-trained models for the target task and select best ones from the model zoo \…
Bi-tuning of Pre-trained Representations
Jincheng Zhong, Ximei Wang, Zhi Kou +2
It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstrea…
Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
Zhiyu Yao, Yunbo Wang, Mingsheng Long +1
This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that fo…
On Localized Discrepancy for Domain Adaptation
Yuchen Zhang, Mingsheng Long, Jianmin Wang +1
We propose the discrepancy-based generalization theories for unsupervised domain adaptation. Previous theories introduced distribution discrepancies defined as the supremum over co…
Transferable Calibration with Lower Bias and Variance in Domain Adaptation
Ximei Wang, Mingsheng Long, Jianmin Wang +1
Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. While remarkable advances have been made, most of the existi…
Minimum Class Confusion for Versatile Domain Adaptation
Ying Jin, Ximei Wang, Mingsheng Long +1
There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-…
Towards Understanding the Transferability of Deep Representations
Hong Liu, Mingsheng Long, Jianmin Wang +1
Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks…
How Does Learning Rate Decay Help Modern Neural Networks?
Kaichao You, Mingsheng Long, Jianmin Wang +1
Learning rate decay (lrDecay) is a \emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empi…
Bridging Theory and Algorithm for Domain Adaptation
Yuchen Zhang, Tianle Liu, Mingsheng Long +1
This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimiza…
WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
Binhang Yuan, Chen Wang, Chen Luo +4
Wind power, as an alternative to burning fossil fuels, is abundant and inexhaustible. To fully utilize wind power, wind farms are usually located in areas of high altitude and faci…
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics
Yunbo Wang, Jianjin Zhang, Hongyu Zhu +3
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel…
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
Yunbo Wang, Zhifeng Gao, Mingsheng Long +2
We present PredRNN++, an improved recurrent network for video predictive learning. In pursuit of a greater spatiotemporal modeling capability, our approach increases the transition…
Partial Transfer Learning with Selective Adversarial Networks
Zhangjie Cao, Mingsheng Long, Jianmin Wang +1
Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains.…
Conditional Adversarial Domain Adaptation
Mingsheng Long, Zhangjie Cao, Jianmin Wang +1
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation metho…
HashNet: Deep Learning to Hash by Continuation
Zhangjie Cao, Mingsheng Long, Jianmin Wang +1
Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep…
Deep Transfer Learning with Joint Adaptation Networks
Mingsheng Long, Han Zhu, Jianmin Wang +1
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint a…
Unsupervised Domain Adaptation with Residual Transfer Networks
Mingsheng Long, Han Zhu, Jianmin Wang +1
The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner…
Learning Multiple Tasks with Multilinear Relationship Networks
Mingsheng Long, Zhangjie Cao, Jianmin Wang +1
Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific alo…