Search Results for author:
Found 54 papers, 29 papers with code
FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning
Concretely, we design an attention-based adapter for the large model, CLIP, and the rest operations merely depend on adapters.
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective
In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective.
SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance.
An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
While standard SSL assumes uniform data distribution, we consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data.
GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective
Pre-trained language models (PLMs) are known to improve the generalization performance of natural language understanding models by leveraging large amounts of data during the pre-training phase.
Natural Language Understanding
Out-of-Distribution Generalization
FIXED: Frustratingly Easy Domain Generalization with Mixup
Firstly, Mixup cannot effectively identify the domain and class information that can be used for learning invariant representations.
Out-of-Distribution Representation Learning for Time Series Classification
Time series classification is an important problem in real world.
Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution
For optimization, we utilize an adapted Mixup to generate an out-of-distribution dataset that can guide the preference direction and optimize with Pareto optimization.
Domain-Specific Risk Minimization for Out-of-Distribution Generalization
Our bound motivates two strategies to reduce the gap: the first one is ensembling multiple classifiers to enrich the hypothesis space, then we propose effective gap estimation methods for guiding the selection of a better hypothesis for the target.
Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction
Limited labeled data increase the risk of distribution shift between test data and training data.
Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets
Beyond classification, Conv-Adapter can generalize to detection and segmentation tasks with more than 50% reduction of parameters but comparable performance to the traditional full fine-tuning.
USB: A Unified Semi-supervised Learning Benchmark for Classification
We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning.
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift
To formally analyze this issue, we provide a unique algebraic formulation of the combination shift problem based on the concepts of homomorphism, equivariance, and a refined definition of disentanglement.
Domain-invariant Feature Exploration for Domain Generalization
Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i. e., the property within a domain, which is agnostic to other domains.
Domain Generalization for Activity Recognition via Adaptive Feature Fusion
To this end, we propose \emph{Adaptive Feature Fusion for Activity Recognition~(AFFAR)}, a domain generalization approach that learns to fuse the domain-invariant and domain-specific representations to improve the model's generalization performance.
Memory-Guided Multi-View Multi-Domain Fake News Detection
In this paper, we propose a Memory-guided Multi-view Multi-domain Fake News Detection Framework (M$^3$FEND) to address these two challenges.
Boosting Cross-Domain Speech Recognition with Self-Supervision
The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Decoupled Federated Learning for ASR with Non-IID Data
Secondly, to reduce the communication and computation costs, we propose decoupled federated learning (DecoupleFL).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcare
Federated learning has attracted increasing attention to building models without accessing the raw user data, especially in healthcare.
Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition
Training on existing data often makes the model biased towards the distribution of the training data, thus the model might perform terribly on test data with different distributions.
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization.
Multi-Representation Adaptation Network for Cross-domain Image Classification
Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects.
Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection
In this paper, we propose a novel approach called Adaptive Memory Network with Self-supervised Learning (AMSL) to address these challenges and enhance the generalization ability in unsupervised anomaly detection.
Margin Calibration for Long-Tailed Visual Recognition
The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i. e., the model tends to classify tail classes as head classes.
Personalized Federated Learning with Adaptive Batchnorm for Healthcare
There is a growing interest in applying machine learning techniques to healthcare.
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select unlabeled data that contribute to the training, thus failing to consider different learning status and learning difficulties of different classes.
Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR
In this work, in order to build a better pre-trained model for low-resource ASR, we propose a pre-training approach called wav2vec-S, where we use task-specific semi-supervised pre-training to refine the self-supervised pre-trained model for the ASR task thus more effectively utilize the capacity of the pre-trained model to generate task-specific representations for ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification
In this paper, we propose to view the time series classification problem from the distribution perspective.
AdaRNN: Adaptive Learning and Forecasting of Time Series
This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data.
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
We empirically compare the proposed approach with several state-of-the-art anomaly detection methods on HAR and HC datasets.
Deep Subdomain Adaptation Network for Image Classification
The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation.
FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare
The success of machine learning applications often needs a large quantity of data.
Exploiting Adapters for Cross-lingual Low-resource Speech Recognition
Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters.
Ranked #1 on
Cross-Lingual ASR
on Common Voice
Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching
End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data.
Ranked #1 on
Cross-environment ASR
on Libri-Adapt
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Learning Invariant Representations across Domains and Tasks
Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19 image classification.
Generalizing to Unseen Domains: A Survey on Domain Generalization
Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.
MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition
In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Adversarial example generation with AdaBelief Optimizer and Crop Invariance
ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks.
Cross-domain Activity Recognition via Substructural Optimal Transport
In this paper, we propose substructure-level matching for domain adaptation (SSDA) to better utilize the locality information of activity data for accurate and efficient knowledge transfer.
Boosting Adversarial Attacks on Neural Networks with Better Optimizer
However, the success rate of adversarial attacks can be further improved in black-box environments.
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
Learning to Match Distributions for Domain Adaptation
However, it remains challenging to determine which method is suitable for a given application since they are built with certain priors or bias.
Joint Partial Optimal Transport for Open Set Domain Adaptation
However, in a general setting when the target domain contains classes that are never observed in the source domain, namely in Open Set Domain Adaptation (OSDA), existing DA methods failed to work because of the interference of the extra unknown classes.
Transfer Learning with Dynamic Adversarial Adaptation Network
In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions.
Transfer Learning with Dynamic Distribution Adaptation
Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions.
Ranked #6 on
Domain Adaptation
on ImageCLEF-DA
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
It is able to achieve accurate and personalized healthcare without compromising privacy and security.
Easy Transfer Learning By Exploiting Intra-domain Structures
In this paper, we propose a practically Easy Transfer Learning (EasyTL) approach which requires no model selection and hyperparameter tuning, while achieving competitive performance.
Ranked #5 on
Transfer Learning
on Office-Home
Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
In this paper, we propose a unified Transfer Channel Pruning (TCP) approach for accelerating UDA models.
Deep Transfer Learning for Cross-domain Activity Recognition
In this paper, we propose an effective Unsupervised Source Selection algorithm for Activity Recognition (USSAR).
Cross-Domain Activity Recognition
Human Activity Recognition
+1
Visual Domain Adaptation with Manifold Embedded Distribution Alignment
Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning.
Ranked #1 on
Domain Adaptation
on Office-Caltech-10
Balanced Distribution Adaptation for Transfer Learning
To tackle the distribution adaptation problem, in this paper, we propose a novel transfer learning approach, named as Balanced Distribution \underline{A}daptation~(BDA), which can adaptively leverage the importance of the marginal and conditional distribution discrepancies, and several existing methods can be treated as special cases of BDA.
Cross-position Activity Recognition with Stratified Transfer Learning
STL consists of two components: Stratified Domain Selection (STL-SDS) can select the most similar source domain to the target domain; Stratified Activity Transfer (STL-SAT) is able to perform accurate knowledge transfer.
Stratified Transfer Learning for Cross-domain Activity Recognition
The proposed framework, referred to as Stratified Transfer Learning (STL), can dramatically improve the classification accuracy for cross-domain activity recognition.
Deep Learning for Sensor-based Activity Recognition: A Survey
This paper surveys the recent advance of deep learning based sensor-based activity recognition.
