Search Results for author:
Found 68 papers, 34 papers with code
Multi-Epoch Learning for Deep Click-Through Rate Prediction Models
However, it is still unknown whether a multi-epoch training paradigm could achieve better results, as the best performance is usually achieved by one-epoch training.
Mind the Label Shift of Augmentation-based Graph OOD Generalization
Recent works employ different graph editions to generate augmented environments and learn an invariant GNN for generalization.
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.
Improving Generalization with Domain Convex Game
A classical solution to DG is domain augmentation, the common belief of which is that diversifying source domains will be conducive to the out-of-distribution generalization.
AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection
Out-of-distribution (OOD) detection is a crucial aspect of deploying machine learning models in open-world applications.
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
To address this issue, we propose a model preprocessing framework, named AdaptGuard, to improve the security of model adaptation algorithms.
MODIFY: Model-driven Face Stylization without Style Images
Briefly, MODIFY first trains a generative model in the target domain and then translates a source input to the target domain via the provided style model.
Exploiting Semantic Attributes for Transductive Zero-Shot Learning
To address this issue, we present a novel transductive ZSL method that produces semantic attributes of the unseen data and imposes them on the generative process.
MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection
Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concerns.
Free Lunch for Domain Adversarial Training: Environment Label Smoothing
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data.
Ranked #3 on
Domain Adaptation
on Office-Home
Learning Feature Recovery Transformer for Occluded Person Re-identification
To reduce the interference of the noise during feature matching, we mainly focus on visible regions that appear in both images and develop a visibility graph to calculate the similarity.
Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
To reduce the training time, we further develop SAC-m that selects CutMix Augmented samples as model inputs, without the need for training the surrogate models or generating adversarial examples.
HORIZON: A High-Resolution Panorama Synthesis Framework
Panorama synthesis aims to generate a visual scene with all 360-degree views and enables an immersive virtual world.
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
To remedy this problem caused by the data heterogeneity, we propose {\sc FedDecorr}, a novel method that can effectively mitigate dimensional collapse in federated learning.
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.
NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis
In this paper, we present NUWA-Infinity, a generative model for infinite visual synthesis, which is defined as the task of generating arbitrarily-sized high-resolution images or long-duration videos.
Ranked #1 on
Image Outpainting
on LHQC
Finding Diverse and Predictable Subgraphs for Graph Domain Generalization
Extensive experiments on both node-level and graph-level benchmarks shows that the proposed DPS achieves impressive performance for various graph domain generalization tasks.
Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
Secondly, we devise a face synthesis module (FSM) to generate a large number of images with stochastic combinations of disentangled identities and attributes for enriching the attribute diversity of synthetic images.
A sentiment analysis model for car review texts based on adversarial training and whole word mask BERT
Based on this, we propose a car review text sentiment analysis model based on adversarial training and whole word mask BERT(ATWWM-BERT).
DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder
Our work proposes a VQ-VAE architecture model with a diffusion decoder (DiVAE) to work as the reconstructing component in image synthesis.
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
First of all, to avoid additional parameters and explore the information in the source model, ProxyMix defines the weights of the classifier as the class prototypes and then constructs a class-balanced proxy source domain by the nearest neighbors of the prototypes to bridge the unseen source domain and the target domain.
Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction
Rich user behavior information is of great importance for capturing and understanding user interest in click-through rate (CTR) prediction.
Causality Inspired Representation Learning for Domain Generalization
Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments.
UMAD: Universal Model Adaptation under Domain and Category Shift
To achieve bilateral adaptation in the target domain, we further maximize localized mutual information to align known samples with the source classifier and employ an entropic loss to push unknown samples far away from the source classification boundary, respectively.
Ranked #2 on
Universal Domain Adaptation
on VisDA2017
Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
Meanwhile, META considers the relevance of an unseen target sample and source domains via normalization statistics and develops an aggregation module to adaptively integrate multiple experts for mimicking unseen target domain.
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance.
Pareto Domain Adaptation
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source.
Incentive Compatible Pareto Alignment for Multi-Source Large Graphs
Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data.
NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion
To cover language, image, and video at the same time for different scenarios, a 3D transformer encoder-decoder framework is designed, which can not only deal with videos as 3D data but also adapt to texts and images as 1D and 2D data, respectively.
Ranked #1 on
Text-to-Video Generation
on Kinetics
Collaborate to Defend Against Adversarial Attacks
However, an ensemble still wastes the limited capacity of multiple models.
Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning
In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources).
Collaboration Equilibrium in Federated Learning
Federated learning (FL) refers to the paradigm of learning models over a collaborative research network involving multiple clients without sacrificing privacy.
Semantic Concentration for Domain Adaptation
To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.
Semi-Supervised Domain Generalizable Person Re-Identification
Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario.
Generalizable Person Re-identification
Knowledge Distillation
+1
Hybrid Reasoning Network for Video-based Commonsense Captioning
Firstly, we develop multi-commonsense learning for semantic-level reasoning by jointly training different commonsense types in a unified network, which encourages the interaction between the clues of multiple commonsense descriptions, event-wise captions and videos.
Source Data-Free Cross-Domain Semantic Segmentation: Align, Teach and Propagate
It is the first work to use negative pseudo labels during self-training for domain adaptation.
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model.
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target).
On Evolving Attention Towards Domain Adaptation
However, considering that the configuration of attention, i. e., the type and the position of attention module, affects the performance significantly, it is more generalized to optimize the attention configuration automatically to be specialized for arbitrary UDA scenario.
Ranked #1 on
Unsupervised Domain Adaptation
on Duke to Market
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
In this paper, we investigate whether applying contrastive learning to fine-tuning would bring further benefits, and analytically find that optimizing the contrastive loss benefits both discriminative representation learning and model optimization during fine-tuning.
Detecting flavor content of the vacuum using the Dirac operator spectrum
We show that we can resolve the flavor content of the sea quarks and constrain their masses using the Dirac spectral density.
High Energy Physics - Lattice High Energy Physics - Phenomenology
A Theory of Self-Supervised Framework for Few-Shot Learning
Recently, self-supervised learning (SSL) algorithms have been applied to Few-shot learning(FSL).
Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples
To craft black-box adversarial examples, adversaries need to query the victim model and take proper advantage of its feedback.
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain.
Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, here in the proposed BCDM, we design a novel classifier determinacy disparity (CDD) metric, which formulates classifier discrepancy as the class relevance of distinct target predictions and implicitly introduces constraint on the target feature discriminability.
A Lane-Changing Prediction Method Based on Temporal Convolution Network
To capture the stochastic time series of lane-changing behavior, this study proposes a temporal convolutional network (TCN) to predict the long-term lane-changing trajectory and behavior.
Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark
Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts.
Robust Finite Mixture Regression for Heterogeneous Targets
FMR is an effective scheme for handling sample heterogeneity, where a single regression model is not enough for capturing the complexities of the conditional distribution of the observed samples given the features.
Domain Agnostic Learning for Unbiased Authentication
We further extend our method to a meta-learning framework to pursue more thorough domain-difference elimination.
Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only a negligible cost, w. r. t.
Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model.
Relation-Guided Representation Learning
In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning.
Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
ATDOC alleviates the classifier bias by introducing an auxiliary classifier for target data only, to improve the quality of pseudo labels.
Why Attentions May Not Be Interpretable?
In this paper, we demonstrate that one root cause of this phenomenon is the combinatorial shortcuts, which means that, in addition to the highlighted parts, the attention weights themselves may carry extra information that could be utilized by downstream models after attention layers.
Adversarial Infidelity Learning for Model Interpretation
A popular way of performing model interpretation is Instance-wise Feature Selection (IFS), which provides an importance score of each feature representing the data samples to explain how the model generates the specific output.
General-Purpose User Embeddings based on Mobile App Usage
In this paper, we report our recent practice at Tencent for user modeling based on mobile app usage.
Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation
To successfully align the multi-modal data structures across domains, the following works exploit discriminative information in the adversarial training process, e. g., using multiple class-wise discriminators and introducing conditional information in input or output of the domain discriminator.
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
On one hand, negative transfer results in misclassification of target samples to the classes only present in the source domain.
Ranked #2 on
Partial Domain Adaptation
on DomainNet
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain.
Ranked #1 on
Domain Adaptation
on USPS-to-MNIST
Deep Learning-Based Least Square Forward-Backward Stochastic Differential Equation Solver for High-Dimensional Derivative Pricing
We propose a new forward-backward stochastic differential equation solver for high-dimensional derivatives pricing problems by combining deep learning solver with least square regression technique widely used in the least square Monte Carlo method for the valuation of American options.
Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation
Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains.
Additive Adversarial Learning for Unbiased Authentication
Authentication is a task aiming to confirm the truth between data instances and personal identities.
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process.
Model-Protected Multi-Task Learning
Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together.
Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
Experimental results on two partial person datasets demonstrate the efficiency and effectiveness of the proposed method in comparison with several state-of-the-art partial person re-id approaches.
Robust Localized Multi-view Subspace Clustering
In multi-view clustering, different views may have different confidence levels when learning a consensus representation.
Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
Object detection when provided image-level labels instead of instance-level labels (i. e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely costly to obtain.
Self-Paced Learning: an Implicit Regularization Perspective
In this paper, we focus on the minimizer function, and study a group of new regularizer, named self-paced implicit regularizer that is deduced from robust loss function.
