Search Results for author: Mingsheng Long

Found 63 papers, 32 papers with code

Ranking and Tuning Pre-trained Models: A New Paradigm of Exploiting Model Hubs

1 code implementation20 Oct 2021 Kaichao You, Yong liu, Jianmin Wang, Michael I. Jordan, Mingsheng Long

In this paper, we propose a new paradigm of exploiting model hubs by ranking and tuning pre-trained models: (1) Our conference work~\citep{you_logme:_2021} proposed LogME to estimate the maximum value of label evidence given features extracted by pre-trained models, which can rank all the PTMs in a model hub for various types of PTMs and tasks \emph{before fine-tuning}.

Omni-Training for Data-Efficient Deep Learning

no code implementations14 Oct 2021 Yang Shu, Zhangjie Cao, Jinghan Gao, Jianmin Wang, Mingsheng Long

Our second contribution is Omni-Loss, in which a mean-teacher regularization is imposed to learn generalizable and stabilized representations.

X-model: Improving Data Efficiency in Deep Learning with A Minimax Model

no code implementations9 Oct 2021 Ximei Wang, Xinyang Chen, Jianmin Wang, Mingsheng Long

To take the power of both worlds, we propose a novel X-model by simultaneously encouraging the invariance to {data stochasticity} and {model stochasticity}.

Age Estimation Object Recognition +1

ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning

no code implementations8 Oct 2021 Zhiyu Yao, Yunbo Wang, Haixu Wu, Jianmin Wang, Mingsheng Long

To this end, we propose ModeRNN, which introduces a novel method to learn structured hidden representations between recurrent states.

Decoupled Adaptation for Cross-Domain Object Detection

1 code implementation6 Oct 2021 Junguang Jiang, Baixu Chen, Jianmin Wang, Mingsheng Long

Besides, previous methods focused on category adaptation but ignored another important part for object detection, i. e., the adaptation on bounding box regression.

Domain Adaptation Object Classification +1

Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

no code implementations6 Oct 2021 Jiehui Xu, Haixu Wu, Jianmin Wang, Mingsheng Long

Technically we propose the \emph{Anomaly Transformer} with an \emph{Anomaly-Attention} mechanism to compute the association discrepancy.

Anomaly Detection Time Series

Zoo-Tuning: Adaptive Transfer from a Zoo of Models

no code implementations29 Jun 2021 Yang Shu, Zhi Kou, Zhangjie Cao, Jianmin Wang, Mingsheng Long

We propose \emph{Zoo-Tuning} to address these challenges, which learns to adaptively transfer the parameters of pretrained models to the target task.

Facial Landmark Detection Image Classification +1

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

no code implementations24 Jun 2021 Haixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long

Also, Transformers have to adopt the sparse versions of point-wise self-attentions for long series efficiency, resulting in the information utilization bottleneck.

Time Series

Transferable Query Selection for Active Domain Adaptation

no code implementations CVPR 2021 Bo Fu, Zhangjie Cao, Jianmin Wang, Mingsheng Long

Due to the domain shift, the query selection criteria of prior active learning methods may be ineffective to select the most informative target samples for annotation.

Active Learning Unsupervised Domain Adaptation

Open Domain Generalization with Domain-Augmented Meta-Learning

no code implementations CVPR 2021 Yang Shu, Zhangjie Cao, Chenyu Wang, Jianmin Wang, Mingsheng Long

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable.

Domain Generalization Meta-Learning

PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning

1 code implementation17 Mar 2021 Yunbo Wang, Haixu Wu, Jianjin Zhang, Zhifeng Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long

This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment.

Video Prediction

Regressive Domain Adaptation for Unsupervised Keypoint Detection

1 code implementation CVPR 2021 Junguang Jiang, Yifei Ji, Ximei Wang, Yufeng Liu, Jianmin Wang, Mingsheng Long

First, based on our observation that the probability density of the output space is sparse, we introduce a spatial probability distribution to describe this sparsity and then use it to guide the learning of the adversarial regressor.

Domain Adaptation Keypoint Detection

Cycle Self-Training for Domain Adaptation

no code implementations5 Mar 2021 Hong Liu, Jianmin Wang, Mingsheng Long

In the forward step, CST generates target pseudo-labels with a source-trained classifier.

Sentiment Analysis Unsupervised Domain Adaptation

MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions

no code implementations CVPR 2021 Haixu Wu, Zhiyu Yao, Jianmin Wang, Mingsheng Long

With high flexibility, this framework can adapt to a series of models for deterministic spatiotemporal prediction.

Video Prediction

Self-Tuning for Data-Efficient Deep Learning

1 code implementation25 Feb 2021 Ximei Wang, Jinghan Gao, Mingsheng Long, Jianmin Wang

Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets.

Transfer Learning

LogME: Practical Assessment of Pre-trained Models for Transfer Learning

1 code implementation22 Feb 2021 Kaichao You, Yong liu, Jianmin Wang, Mingsheng Long

In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models.

Model Selection Transfer Learning

Co-Tuning for Transfer Learning

2 code implementations NeurIPS 2020 Kaichao You, Zhi Kou, Mingsheng Long, Jianmin Wang

Fine-tuning pre-trained deep neural networks (DNNs) to a target dataset, also known as transfer learning, is widely used in computer vision and NLP.

Image Classification Transfer Learning

Learning to Adapt to Evolving Domains

1 code implementation NeurIPS 2020 Hong Liu, Mingsheng Long, Jianmin Wang, Yu Wang

(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.

Meta-Learning Transfer Learning +1

Stochastic Normalization

2 code implementations NeurIPS 2020 Zhi Kou, Kaichao You, Mingsheng Long, Jianmin Wang

During training, two branches are stochastically selected to avoid over-depending on some sample statistics, resulting in a strong regularization effect, which we interpret as ``architecture regularization.''

Bi-tuning of Pre-trained Representations

no code implementations12 Nov 2020 Jincheng Zhong, Ximei Wang, Zhi Kou, Jianmin Wang, Mingsheng Long

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 downstream task.

Contrastive Learning Unsupervised Pre-training

Unsupervised Transfer Learning for Spatiotemporal Predictive Networks

1 code implementation ICML 2020 Zhiyu Yao, Yunbo Wang, Mingsheng Long, Jian-Min Wang

This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks.

Transfer Learning

On Localized Discrepancy for Domain Adaptation

no code implementations14 Aug 2020 Yuchen Zhang, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

Finally, we further extend the localized discrepancies for achieving super transfer and derive generalization bounds that could be even more sample-efficient on source domain.

Generalization Bounds Unsupervised Domain Adaptation

Transferable Calibration with Lower Bias and Variance in Domain Adaptation

no code implementations NeurIPS 2020 Ximei Wang, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target labels.

Decision Making Domain Adaptation

VideoDG: Generalizing Temporal Relations in Videos to Novel Domains

1 code implementation8 Dec 2019 Zhiyu Yao, Yunbo Wang, Jianmin Wang, Philip S. Yu, Mingsheng Long

This paper introduces video domain generalization where most video classification networks degenerate due to the lack of exposure to the target domains of divergent distributions.

Action Recognition Data Augmentation +3

Minimum Class Confusion for Versatile Domain Adaptation

2 code implementations ECCV 2020 Ying Jin, Ximei Wang, Mingsheng Long, Jian-Min Wang

It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7. 3% on DomainNet).

Multi-target Domain Adaptation Partial Domain Adaptation

Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning

2 code implementations NeurIPS 2019 Xinyang Chen, Sinan Wang, Bo Fu, Mingsheng Long, Jian-Min Wang

Before sufficient training data is available, fine-tuning neural networks pre-trained on large-scale datasets substantially outperforms training from random initialization.

Transfer Learning

Towards Understanding the Transferability of Deep Representations

no code implementations26 Sep 2019 Hong Liu, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

3) The feasibility of transferability is related to the similarity of both input and label.

How Does Learning Rate Decay Help Modern Neural Networks?

no code implementations ICLR 2020 Kaichao You, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

Despite the popularity of these common beliefs, experiments suggest that they are insufficient in explaining the general effectiveness of lrDecay in training modern neural networks that are deep, wide, and nonconvex.

Eidetic 3D LSTM: A Model for Video Prediction and Beyond

2 code implementations ICLR 2019 Yunbo Wang, Lu Jiang, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, Li Fei-Fei

We first evaluate the E3D-LSTM network on widely-used future video prediction datasets and achieve the state-of-the-art performance.

Activity Recognition Video Prediction

Bridging Theory and Algorithm for Domain Adaptation

3 code implementations11 Apr 2019 Yuchen Zhang, Tianle Liu, Mingsheng Long, Michael. I. Jordan

We introduce Margin Disparity Discrepancy, a novel measurement with rigorous generalization bounds, tailored to the distribution comparison with the asymmetric margin loss, and to the minimax optimization for easier training.

Domain Adaptation Generalization Bounds

Learning to Transfer Examples for Partial Domain Adaptation

1 code implementation CVPR 2019 Zhangjie Cao, Kaichao You, Mingsheng Long, Jian-Min Wang, Qiang Yang

Under the condition that target labels are unknown, the key challenge of PDA is how to transfer relevant examples in the shared classes to promote positive transfer, and ignore irrelevant ones in the specific classes to mitigate negative transfer.

Partial Domain Adaptation Transfer Learning

Spatiotemporal Pyramid Network for Video Action Recognition

no code implementations CVPR 2017 Yunbo Wang, Mingsheng Long, Jian-Min Wang, Philip S. Yu

From the technical perspective, we introduce the spatiotemporal compact bilinear operator into video analysis tasks.

Action Recognition

Deep Triplet Quantization

1 code implementation1 Feb 2019 Bin Liu, Yue Cao, Mingsheng Long, Jian-Min Wang, Jingdong Wang

We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets.

Image Retrieval Quantization

Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics

2 code implementations CVPR 2019 Yunbo Wang, Jianjin Zhang, Hongyu Zhu, Mingsheng Long, Jian-Min Wang, Philip S. Yu

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 values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting.

Time Series Time Series Forecasting +1

Deep Priority Hashing

1 code implementation4 Sep 2018 Zhangjie Cao, Ziping Sun, Mingsheng Long, Jian-Min Wang, Philip S. Yu

Deep hashing enables image retrieval by end-to-end learning of deep representations and hash codes from training data with pairwise similarity information.

Image Retrieval Quantization

Multi-Adversarial Domain Adaptation

2 code implementations4 Sep 2018 Zhongyi Pei, Zhangjie Cao, Mingsheng Long, Jian-Min Wang

Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains.

Domain Adaptation

Cross-Modal Hamming Hashing

no code implementations ECCV 2018 Yue Cao , Bin Liu, Mingsheng Long, Jian-Min Wang

Extensive experiments demonstrate that CMHH can generate highly concentrated hash codes and achieve state-of-the-art cross-modal retrieval performance for both hash lookups and linear scan scenarios on three benchmark datasets, NUS-WIDE, MIRFlickr-25K, and IAPR TC-12.

Cross-Modal Retrieval

Partial Adversarial Domain Adaptation

2 code implementations ECCV 2018 Zhangjie Cao, Lijia Ma, Mingsheng Long, Jian-Min Wang

We present Partial Adversarial Domain Adaptation (PADA), which simultaneously alleviates negative transfer by down-weighing the data of outlier source classes for training both source classifier and domain adversary, and promotes positive transfer by matching the feature distributions in the shared label space.

Partial Domain Adaptation

HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN

no code implementations CVPR 2018 Yue Cao, Bin Liu, Mingsheng Long, Jian-Min Wang

The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information.

Image Retrieval Representation Learning

Deep Cauchy Hashing for Hamming Space Retrieval

no code implementations CVPR 2018 Yue Cao, Mingsheng Long, Bin Liu, Jian-Min Wang

Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding.

Image Retrieval Representation Learning

Transfer Adversarial Hashing for Hamming Space Retrieval

no code implementations13 Dec 2017 Zhangjie Cao, Mingsheng Long, Chao Huang, Jian-Min Wang

Existing work on deep hashing assumes that the database in the target domain is identically distributed with the training set in the source domain.

Image Retrieval

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

no code implementations NeurIPS 2017 Yunbo Wang, Mingsheng Long, Jian-Min Wang, Zhifeng Gao, Philip S. Yu

The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously.

Video Prediction

Deep Visual-Semantic Quantization for Efficient Image Retrieval

no code implementations CVPR 2017 Yue Cao, Mingsheng Long, Jian-Min Wang, Shichen Liu

This paper presents a compact coding solution with a focus on the deep learning to quantization approach, which improves retrieval quality by end-to-end representation learning and compact encoding and has already shown the superior performance over the hashing solutions for similarity retrieval.

Image Retrieval Quantization +1

Conditional Adversarial Domain Adaptation

3 code implementations NeurIPS 2018 Mingsheng Long, Zhangjie Cao, Jian-Min Wang, Michael. I. Jordan

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation.

Domain Adaptation General Classification

HashNet: Deep Learning to Hash by Continuation

1 code implementation ICCV 2017 Zhangjie Cao, Mingsheng Long, Jian-Min Wang, Philip S. Yu

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.

Binarization Representation Learning

Transitive Hashing Network for Heterogeneous Multimedia Retrieval

no code implementations15 Aug 2016 Zhangjie Cao, Mingsheng Long, Qiang Yang

Hashing has been widely applied to large-scale multimedia retrieval due to the storage and retrieval efficiency.

Correlation Hashing Network for Efficient Cross-Modal Retrieval

no code implementations22 Feb 2016 Yue Cao, Mingsheng Long, Jian-Min Wang, Philip S. Yu

This paper presents a Correlation Hashing Network (CHN) approach to cross-modal hashing, which jointly learns good data representation tailored to hash coding and formally controls the quantization error.

Cross-Modal Retrieval Quantization

Unsupervised Domain Adaptation with Residual Transfer Networks

1 code implementation NeurIPS 2016 Mingsheng Long, Han Zhu, Jian-Min Wang, Michael. I. Jordan

In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain.

Unsupervised Domain Adaptation

Learning Multiple Tasks with Multilinear Relationship Networks

no code implementations NeurIPS 2017 Mingsheng Long, Zhangjie Cao, Jian-Min Wang, Philip S. Yu

Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks.

Multi-Task Learning

Learning Transferable Features with Deep Adaptation Networks

4 code implementations10 Feb 2015 Mingsheng Long, Yue Cao, Jian-Min Wang, Michael. I. Jordan

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation.

Domain Adaptation Image Classification

Transfer Joint Matching for Unsupervised Domain Adaptation

no code implementations CVPR 2014 Mingsheng Long, Jian-Min Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu

Visual domain adaptation, which learns an accurate classifier for a new domain using labeled images from an old domain, has shown promising value in computer vision yet still been a challenging problem.

Dimensionality Reduction Unsupervised Domain Adaptation

Transfer Sparse Coding for Robust Image Representation

no code implementations CVPR 2013 Mingsheng Long, Guiguang Ding, Jian-Min Wang, Jiaguang Sun, Yuchen Guo, Philip S. Yu

In this paper, we propose a Transfer Sparse Coding (TSC) approach to construct robust sparse representations for classifying cross-distribution images accurately.

Cannot find the paper you are looking for? You can Submit a new open access paper.