Search Results for author:
Found 97 papers, 59 papers with code
Learning to Detect Open Classes for Universal Domain Adaptation
The new transferability measure accurately quantifies the inclination of a target example to the open classes.
Ranked #8 on
Universal Domain Adaptation
on DomainNet
depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers
PyTorch \texttt{2. x} introduces a compiler designed to accelerate deep learning programs.
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Experimentally, TimeXer significantly improves time series forecasting with exogenous variables and achieves consistent state-of-the-art performance in twelve real-world forecasting benchmarks.
EuLagNet: Eulerian Fluid Prediction with Lagrangian Dynamics
Accurately predicting the future fluid is important to extensive areas, such as meteorology, oceanology and aerodynamics.
TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling
To emphasize temporal correlation modeling, this paper proposes TimeSiam as a simple but effective self-supervised pre-training framework for Time series based on Siamese networks.
Transolver: A Fast Transformer Solver for PDEs on General Geometries
Transformers have empowered many milestones across various fields and have recently been applied to solve partial differential equations (PDEs).
Timer: Transformers for Time Series Analysis at Scale
Continuous progresses have been achieved as the emergence of large language models, exhibiting unprecedented ability in few-shot generalization, scalability, and task generality, which is however absent in time series models.
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
Foundation models of time series have not been fully developed due to the limited availability of large-scale time series and the underexploration of scalable pre-training.
HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction
Compared with previous velocity estimating methods, HelmFluid is faithfully derived from Helmholtz theorem and ravels out complex fluid dynamics with physically interpretable evidence.
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series, with each token formed by multiple variates of the same timestamp.
On the Embedding Collapse when Scaling up Recommendation Models
Recent advances in deep foundation models have led to a promising trend of developing large recommendation models to leverage vast amounts of available data.
HarmonyDream: Task Harmonization Inside World Models
Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward modeling.
Ranked #4 on
Atari Games 100k
on Atari 100k
Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
While previous models suffer from complicated series variations induced by changing temporal distribution, we tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics.
Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes.
Efficient ConvBN Blocks for Transfer Learning and Beyond
Subsequently, we propose a novel Tune mode to bridge the gap between Eval mode and Deploy mode.
CLIPood: Generalizing CLIP to Out-of-Distributions
This paper aims at generalizing CLIP to out-of-distribution test data on downstream tasks.
SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
By relating masked modeling to manifold learning, SimMTM proposes to recover masked time points by the weighted aggregation of multiple neighbors outside the manifold, which eases the reconstruction task by assembling ruined but complementary temporal variations from multiple masked series.
Solving High-Dimensional PDEs with Latent Spectral Models
A burgeoning paradigm is learning neural operators to approximate the input-output mappings of PDEs.
ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks.
Out-of-Dynamics Imitation Learning from Multimodal Demonstrations
Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator.
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block.
Recommender Transformers with Behavior Pathways
We conclude this characteristic for sequential behaviors of each user as the Behavior Pathway.
Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models
The proposed framework can be trained end-to-end with the target task-specific loss, where it learns to explore better pathway configurations and exploit the knowledge in pre-trained models for each target datum.
Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.
MetaSets: Meta-Learning on Point Sets for Generalizable Representations
It is a challenging problem due to the substantial geometry shift from simulated to real data, such that most existing 3D models underperform due to overfitting the complete geometries in the source domain.
Continual Predictive Learning from Videos
Can we develop predictive learning algorithms that can deal with more realistic, non-stationary physical environments?
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
From Big to Small: Adaptive Learning to Partial-Set Domains
Still, the common requirement of identical class space shared across domains hinders applications of domain adaptation to partial-set domains.
Debiased Self-Training for Semi-Supervised Learning
Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks.
Flowformer: Linearizing Transformers with Conservation Flows
By respectively conserving the incoming flow of sinks for source competition and the outgoing flow of sources for sink allocation, Flow-Attention inherently generates informative attentions without using specific inductive biases.
Ranked #4 on
D4RL
on D4RL
Supported Policy Optimization for Offline Reinforcement Learning
Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy.
Transferability in Deep Learning: A Survey
The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks.
Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
(2) The best ranked PTM can either be fine-tuned and deployed if we have no preference for the model's architecture or the target PTM can be tuned by the top $K$ ranked PTMs via a Bayesian procedure that we propose.
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning
While pre-training and meta-training can create deep models powerful for few-shot generalization, we find that pre-training and meta-training focuses respectively on cross-domain transferability and cross-task transferability, which restricts their data efficiency in the entangled settings of domain shift and task shift.
X-model: Improving Data Efficiency in Deep Learning with A Minimax Model
To take the power of both worlds, we propose a novel X-model by simultaneously encouraging the invariance to {data stochasticity} and {model stochasticity}.
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning
To this end, we propose ModeRNN, which introduces a novel method to learn structured hidden representations between recurrent states.
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
Unsupervised detection of anomaly points in time series is a challenging problem, which requires the model to derive a distinguishable criterion.
Decoupled Adaptation for Cross-Domain Object Detection
Besides, previous methods focused on category adaptation but ignored another important part for object detection, i. e., the adaptation on bounding box regression.
Zoo-Tuning: Adaptive Transfer from a Zoo of Models
We propose \emph{Zoo-Tuning} to address these challenges, which learns to adaptively transfer the parameters of pretrained models to the target task.
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
Going beyond Transformers, we design Autoformer as a novel decomposition architecture with an Auto-Correlation mechanism.
Transferable Query Selection for Active Domain Adaptation
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.
MetaSets：Meta-Learning on Point Sets for Generalizable Representations
It is a challenging problem due to the substantial geometry shift from simulated to real data, such that most existing 3D models underperform due to overfitting the complete geometries in the source domain.
Open Domain Generalization with Domain-Augmented Meta-Learning
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.
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
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.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Regressive Domain Adaptation for Unsupervised Keypoint Detection
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.
Cycle Self-Training for Domain Adaptation
In the forward step, CST generates target pseudo-labels with a source-trained classifier.
MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
With high flexibility, this framework can adapt to a series of models for deterministic spatiotemporal prediction.
Self-Tuning for Data-Efficient Deep Learning
Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets.
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models.
Ranked #3 on
Transferability
on classification benchmark
Stochastic Normalization
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.''
Co-Tuning for Transfer Learning
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.
Ranked #1 on
Transfer Learning
on COCO70
Learning to Adapt to Evolving Domains
(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.
Bi-tuning of Pre-trained Representations
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.
Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks.
On Localized Discrepancy for Domain Adaptation
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.
Transferable Calibration with Lower Bias and Variance in Domain Adaptation
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.
Negative Margin Matters: Understanding Margin in Few-shot Classification
This paper introduces a negative margin loss to metric learning based few-shot learning methods.
VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
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.
Minimum Class Confusion for Versatile Domain Adaptation
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).
Ranked #3 on
Multi-target Domain Adaptation
on DomainNet
Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
Deep neural networks (DNNs) excel at learning representations when trained on large-scale datasets.
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
Before sufficient training data is available, fine-tuning neural networks pre-trained on large-scale datasets substantially outperforms training from random initialization.
Towards Understanding the Transferability of Deep Representations
3) The feasibility of transferability is related to the similarity of both input and label.
How Does Learning Rate Decay Help Modern Neural Networks?
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.
Z-Order Recurrent Neural Networks for Video Prediction
First, we propose a new RNN architecture for modeling the deterministic dynamics, which updates hidden states along a z-order curve to enhance the consistency of the features of mirrored layers.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
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 domain.
Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation
In this paper, a series of experiments based on spectral analysis of the feature representations have been conducted, revealing an unexpected deterioration of the discriminability while learning transferable features adversarially.
Eidetic 3D LSTM: A Model for Video Prediction and Beyond
We first evaluate the E3D-LSTM network on widely-used future video prediction datasets and achieve the state-of-the-art performance.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Bridging Theory and Algorithm for Domain Adaptation
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.
Learning to Transfer Examples for Partial Domain Adaptation
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.
Ranked #4 on
Partial Domain Adaptation
on ImageNet-Caltech
Spatiotemporal Pyramid Network for Video Action Recognition
From the technical perspective, we introduce the spatiotemporal compact bilinear operator into video analysis tasks.
WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
Quick detection of blade ice accretion is crucial for the maintenance of wind farms.
Deep Triplet Quantization
We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets.
Ranked #1 on
Image Retrieval
on NUS-WIDE
Generalized Zero-Shot Learning with Deep Calibration Network
A technical challenge of deep learning is recognizing target classes without seen data.
Multi-Task Learning of Generalizable Representations for Video Action Recognition
Rev2Net is shown to be effective on the classic action recognition task.
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics
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.
Ranked #5 on
Video Prediction
on Human3.6M
Deep Priority Hashing
Deep hashing enables image retrieval by end-to-end learning of deep representations and hash codes from training data with pairwise similarity information.
Multi-Adversarial Domain Adaptation
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.
Ranked #25 on
Domain Adaptation
on Office-31
Cross-Modal Hamming Hashing
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.
Partial Adversarial Domain Adaptation
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.
Ranked #3 on
Partial Domain Adaptation
on DomainNet
Predcnn: Predictive learning with cascade convolutions
Predicting future frames in videos remains an unsolved but challenging problem.
Ranked #3 on
Pose Prediction
on Filtered NTU RGB+D
HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN
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.
Deep Cauchy Hashing for Hamming Space Retrieval
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.
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
We present PredRNN++, an improved recurrent network for video predictive learning.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Transfer Adversarial Hashing for Hamming Space Retrieval
Existing work on deep hashing assumes that the database in the target domain is identically distributed with the training set in the source domain.
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously.
Ranked #6 on
Video Prediction
on Human3.6M
Partial Transfer Learning with Selective Adversarial Networks
Existing domain adversarial networks assume fully shared label space across domains.
Deep Visual-Semantic Quantization for Efficient Image Retrieval
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.
Conditional Adversarial Domain Adaptation
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation.
Ranked #6 on
Domain Adaptation
on USPS-to-MNIST
HashNet: Deep Learning to Hash by Continuation
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.
Transitive Hashing Network for Heterogeneous Multimedia Retrieval
Hashing has been widely applied to large-scale multimedia retrieval due to the storage and retrieval efficiency.
Deep Transfer Learning with Joint Adaptation Networks
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain.
Ranked #2 on
Domain Adaptation
on HMDBfull-to-UCF
Multi-Source Unsupervised Domain Adaptation
Transfer Learning
Correlation Hashing Network for Efficient Cross-Modal Retrieval
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.
Unsupervised Domain Adaptation with Residual Transfer Networks
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.
Learning Multiple Tasks with Multilinear Relationship Networks
Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks.
Learning Transferable Features with Deep Adaptation Networks
Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation.
Ranked #3 on
Domain Adaptation
on Synth Digits-to-SVHN
Transfer Joint Matching for Unsupervised Domain Adaptation
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.
Transfer Sparse Coding for Robust Image Representation
In this paper, we propose a Transfer Sparse Coding (TSC) approach to construct robust sparse representations for classifying cross-distribution images accurately.
