2.8k citations · 7.4k across the 41 of their papers we have counts for
41 papers
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…
Electronic properties of twisted bilayer graphene suspended and encapsulated with hexagonal boron nitride
Min Long, Zhen Zhan, Pierre A. Pantaleón +3
The recent observed anomalous Hall effect in magic angle twisted bilayer graphene (TBG) aligned to hexagonal boron nitride (hBN) and unconventional ferroelectricity in Bernal bilay…
An accurate description of the structural and electronic properties of twisted bilayer graphene-boron nitride heterostructures
Min Long, Pierre A. Pantaleón, Zhen Zhan +3
Twisted bilayer graphene (TBG) has taken the spotlight in the condensed matter community since the discovery of correlated phases at the so-called magic angle. Interestingly, the r…
Regressive Domain Adaptation for Unsupervised Keypoint Detection
Junguang Jiang, Yifei Ji, Ximei Wang +3
Domain adaptation (DA) aims at transferring knowledge from a labeled source domain to an unlabeled target domain. Though many DA theories and algorithms have been proposed, most of…
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…
MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
Haixu Wu, Zhiyu Yao, Jianmin Wang +1
This paper tackles video prediction from a new dimension of predicting spacetime-varying motions that are incessantly changing across both space and time. Prior methods mainly capt…
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…
Negative Margin Matters: Understanding Margin in Few-shot Classification
Bin Liu, Yue Cao, Yutong Lin +4
This paper introduces a negative margin loss to metric learning based few-shot learning methods. The negative margin loss significantly outperforms regular softmax loss, and achiev…
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…
Learning to Transfer Examples for Partial Domain Adaptation
Zhangjie Cao, Kaichao You, Mingsheng Long +2
Domain adaptation is critical for learning in new and unseen environments. With domain adversarial training, deep networks can learn disentangled and transferable features that eff…
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…
Spatiotemporal Pyramid Network for Video Action Recognition
Yunbo Wang, Mingsheng Long, Jianmin Wang +1
Two-stream convolutional networks have shown strong performance in video action recognition tasks. The key idea is to learn spatiotemporal features by fusing convolutional networks…
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…
Deep Triplet Quantization
Bin Liu, Yue Cao, Mingsheng Long +2
Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding sol…