Search Results for author: Jian Liang

Found 68 papers, 34 papers with code

Multi-Epoch Learning for Deep Click-Through Rate Prediction Models

no code implementations31 May 2023 Zhaocheng Liu, Zhongxiang Fan, Jian Liang, Dongying Kong, Han Li

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.

Click-Through Rate Prediction Data Augmentation

Mind the Label Shift of Augmentation-based Graph OOD Generalization

no code implementations CVPR 2023 Junchi Yu, Jian Liang, Ran He

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

1 code implementation27 Mar 2023 Jian Liang, Ran He, Tieniu Tan

Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.

Source-Free Domain Adaptation

Improving Generalization with Domain Convex Game

1 code implementation CVPR 2023 Fangrui Lv, Jian Liang, Shuang Li, Jinming Zhang, Di Liu

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.

Domain Generalization Out-of-Distribution Generalization

AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection

no code implementations22 Mar 2023 Puning Yang, Jian Liang, Jie Cao, Ran He

Out-of-distribution (OOD) detection is a crucial aspect of deploying machine learning models in open-world applications.

Out of Distribution (OOD) Detection

AdaptGuard: Defending Against Universal Attacks for Model Adaptation

no code implementations19 Mar 2023 Lijun Sheng, Jian Liang, Ran He, Zilei Wang, Tieniu Tan

To address this issue, we propose a model preprocessing framework, named AdaptGuard, to improve the security of model adaptation algorithms.

Knowledge Distillation Transfer Learning

MODIFY: Model-driven Face Stylization without Style Images

no code implementations17 Mar 2023 Yuhe Ding, Jian Liang, Jie Cao, Aihua Zheng, Ran He

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

no code implementations17 Mar 2023 Zhengbo Wang, Jian Liang, Zilei Wang, Tieniu Tan

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.

Zero-Shot Learning

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

no code implementations9 Feb 2023 Yuhe Ding, Jian Liang, Bo Jiang, Aihua Zheng, Ran He

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.

Data Augmentation Keypoint Detection

Learning Feature Recovery Transformer for Occluded Person Re-identification

1 code implementation5 Jan 2023 Boqiang Xu, Lingxiao He, Jian Liang, Zhenan Sun

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.

Graph Matching Graph Similarity +1

Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks

1 code implementation21 Oct 2022 Jiyang Guan, Jian Liang, Ran He

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.

Adversarial Defense Transfer Learning

HORIZON: A High-Resolution Panorama Synthesis Framework

no code implementations10 Oct 2022 Kun Yan, Lei Ji, Chenfei Wu, Jian Liang, Ming Zhou, Nan Duan, Shuai Ma

Panorama synthesis aims to generate a visual scene with all 360-degree views and enables an immersive virtual world.

Vocal Bursts Intensity Prediction

Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

2 code implementations1 Oct 2022 Yujun Shi, Jian Liang, Wenqing Zhang, Vincent Y. F. Tan, Song Bai

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.

Federated Learning

Domain-Specific Risk Minimization for Out-of-Distribution Generalization

1 code implementation18 Aug 2022 Yi-Fan Zhang, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, DaCheng Tao, Xing Xie

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.

Domain Generalization Out-of-Distribution Generalization

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

1 code implementation20 Jul 2022 Chenfei Wu, Jian Liang, Xiaowei Hu, Zhe Gan, JianFeng Wang, Lijuan Wang, Zicheng Liu, Yuejian Fang, Nan Duan

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.

Image Outpainting Text-to-Image Generation +1

Finding Diverse and Predictable Subgraphs for Graph Domain Generalization

no code implementations19 Jun 2022 Junchi Yu, Jian Liang, Ran He

Extensive experiments on both node-level and graph-level benchmarks shows that the proposed DPS achieves impressive performance for various graph domain generalization tasks.

Domain Generalization Out-of-Distribution Generalization

Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement

no code implementations10 Jun 2022 Ziming Yang, Jian Liang, Chaoyou Fu, Mandi Luo, Xiao-Yu Zhang

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.

Data Augmentation Disentanglement +3

A sentiment analysis model for car review texts based on adversarial training and whole word mask BERT

no code implementations6 Jun 2022 Xingchen Liu, Yawen Li, Yingxia Shao, Ang Li, Jian Liang

Based on this, we propose a car review text sentiment analysis model based on adversarial training and whole word mask BERT(ATWWM-BERT).

Decision Making Sentiment Analysis

DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder

no code implementations1 Jun 2022 Jie Shi, Chenfei Wu, Jian Liang, Xiang Liu, Nan Duan

Our work proposes a VQ-VAE architecture model with a diffusion decoder (DiVAE) to work as the reconstructing component in image synthesis.

Denoising Image Generation

ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

1 code implementation29 May 2022 Yuhe Ding, Lijun Sheng, Jian Liang, Aihua Zheng, Ran He

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.

Object Recognition Source-Free Domain Adaptation +1

Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction

no code implementations25 Apr 2022 Xiaochen Li, Rui Zhong, Jian Liang, Xialong Liu, Yu Zhang

Rich user behavior information is of great importance for capturing and understanding user interest in click-through rate (CTR) prediction.

Click-Through Rate Prediction

Causality Inspired Representation Learning for Domain Generalization

1 code implementation CVPR 2022 Fangrui Lv, Jian Liang, Shuang Li, Bin Zang, Chi Harold Liu, Ziteng Wang, Di Liu

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.

Domain Generalization Representation Learning

UMAD: Universal Model Adaptation under Domain and Category Shift

no code implementations16 Dec 2021 Jian Liang, Dapeng Hu, Jiashi Feng, Ran He

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.

Universal Domain Adaptation Unsupervised Domain Adaptation

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

1 code implementation16 Dec 2021 Boqiang Xu, Jian Liang, Lingxiao He, Zhenan Sun

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.

Generalizable Person Re-identification

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

1 code implementation CVPR 2022 Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip Torr, Song Bai, Vincent Y. F. Tan

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.

class-incremental learning Class Incremental Learning +1

Pareto Domain Adaptation

1 code implementation NeurIPS 2021 Fangrui Lv, Jian Liang, Kaixiong Gong, Shuang Li, Chi Harold Liu, Han Li, Di Liu, Guoren Wang

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.

Domain Adaptation Image Classification +2

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

1 code implementation6 Dec 2021 Jian Liang, Fangrui Lv, Di Liu, Zehui Dai, Xu Tian, Shuang Li, Fei Wang, Han Li

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

1 code implementation24 Nov 2021 Chenfei Wu, Jian Liang, Lei Ji, Fan Yang, Yuejian Fang, Daxin Jiang, Nan Duan

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.

Text-to-Image Generation Text-to-Video Generation +2

Collaborate to Defend Against Adversarial Attacks

no code implementations29 Sep 2021 Sen Cui, Jingfeng Zhang, Jian Liang, Masashi Sugiyama, ChangShui Zhang

However, an ensemble still wastes the limited capacity of multiple models.

Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning

1 code implementation NeurIPS 2021 Sen Cui, Weishen Pan, Jian Liang, ChangShui Zhang, Fei Wang

In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources).

Fairness Federated Learning

Collaboration Equilibrium in Federated Learning

1 code implementation18 Aug 2021 Sen Cui, Jian Liang, Weishen Pan, Kun Chen, ChangShui Zhang, Fei Wang

Federated learning (FL) refers to the paradigm of learning models over a collaborative research network involving multiple clients without sacrificing privacy.

Federated Learning

Semantic Concentration for Domain Adaptation

1 code implementation ICCV 2021 Shuang Li, Mixue Xie, Fangrui Lv, Chi Harold Liu, Jian Liang, Chen Qin, Wei Li

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.

Domain Adaptation Transfer Learning

Semi-Supervised Domain Generalizable Person Re-Identification

3 code implementations11 Aug 2021 Lingxiao He, Wu Liu, Jian Liang, Kecheng Zheng, Xingyu Liao, Peng Cheng, Tao Mei

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

1 code implementation5 Aug 2021 Weijiang Yu, Jian Liang, Lei Ji, Lu Li, Yuejian Fang, Nong Xiao, Nan Duan

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.

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

no code implementations NeurIPS 2021 Mi Luo, Fei Chen, Dapeng Hu, Yifan Zhang, Jian Liang, Jiashi Feng

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.

Classifier calibration Federated Learning

DINE: Domain Adaptation from Single and Multiple Black-box Predictors

3 code implementations CVPR 2022 Jian Liang, Dapeng Hu, Jiashi Feng, Ran He

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).

Transductive Learning Unsupervised Domain Adaptation

On Evolving Attention Towards Domain Adaptation

no code implementations25 Mar 2021 Kekai Sheng, Ke Li, Xiawu Zheng, Jian Liang, WeiMing Dong, Feiyue Huang, Rongrong Ji, Xing Sun

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.

Partial Domain Adaptation Unsupervised Domain Adaptation

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

1 code implementation NeurIPS 2021 Yifan Zhang, Bryan Hooi, Dapeng Hu, Jian Liang, Jiashi Feng

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.

Contrastive Learning Image Classification +4

Detecting flavor content of the vacuum using the Dirac operator spectrum

no code implementations10 Feb 2021 Jian Liang, Andrei Alexandru, Yu-Jiang Bi, Terrence Draper, Keh-Fei Liu, Yi-Bo Yang

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

Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples

no code implementations ICLR 2021 Ziang Yan, Yiwen Guo, Jian Liang, ChangShui Zhang

To craft black-box adversarial examples, adversaries need to query the victim model and take proper advantage of its feedback.

Image Classification

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

2 code implementations14 Dec 2020 Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, Jiashi Feng

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.

Classification General Classification +3

Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation

1 code implementation13 Dec 2020 Shuang Li, Fangrui Lv, Binhui Xie, Chi Harold Liu, Jian Liang, Chen Qin

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.

Semantic Segmentation

A Lane-Changing Prediction Method Based on Temporal Convolution Network

no code implementations1 Nov 2020 Yue Zhang, Yajie Zou, Jinjun Tang, Jian Liang

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.

Time Series Analysis

Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark

no code implementations15 Oct 2020 Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Conghui Zhu, Tiejun Zhao

Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts.

Natural Language Inference

Robust Finite Mixture Regression for Heterogeneous Targets

no code implementations12 Oct 2020 Jian Liang, Kun Chen, Ming Lin, ChangShui Zhang, Fei Wang

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.

feature selection regression

Domain Agnostic Learning for Unbiased Authentication

no code implementations11 Oct 2020 Jian Liang, Yuren Cao, Shuang Li, Bing Bai, Hao Li, Fei Wang, Kun Bai

We further extend our method to a meta-learning framework to pursue more thorough domain-difference elimination.

Face Recognition Meta-Learning +1

Hybrid Differentially Private Federated Learning on Vertically Partitioned Data

no code implementations6 Sep 2020 Chang Wang, Jian Liang, Mingkai Huang, Bing Bai, Kun Bai, Hao Li

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.

Federated Learning Privacy Preserving

Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning

1 code implementation25 Aug 2020 Yinghua Zhang, Yangqiu Song, Jian Liang, Kun Bai, Qiang Yang

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.

Transfer Learning

Relation-Guided Representation Learning

no code implementations11 Jul 2020 Zhao Kang, Xiao Lu, Jian Liang, Kun Bai, Zenglin Xu

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.

Representation Learning

Domain Adaptation with Auxiliary Target Domain-Oriented Classifier

2 code implementations CVPR 2021 Jian Liang, Dapeng Hu, Jiashi Feng

ATDOC alleviates the classifier bias by introducing an auxiliary classifier for target data only, to improve the quality of pseudo labels.

Domain Adaptation Transfer Learning

Why Attentions May Not Be Interpretable?

no code implementations10 Jun 2020 Bing Bai, Jian Liang, Guanhua Zhang, Hao Li, Kun Bai, Fei Wang

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.

Feature Importance

Adversarial Infidelity Learning for Model Interpretation

1 code implementation9 Jun 2020 Jian Liang, Bing Bai, Yuren Cao, Kun Bai, Fei Wang

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.

feature selection

General-Purpose User Embeddings based on Mobile App Usage

1 code implementation27 May 2020 Junqi Zhang, Bing Bai, Ye Lin, Jian Liang, Kun Bai, Fei Wang

In this paper, we report our recent practice at Tencent for user modeling based on mobile app usage.

Feature Engineering

Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation

no code implementations30 Mar 2020 Dapeng Hu, Jian Liang, Qibin Hou, Hanshu Yan, Yunpeng Chen, Shuicheng Yan, Jiashi Feng

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.

Object Recognition Semantic Segmentation +1

Deep Learning-Based Least Square Forward-Backward Stochastic Differential Equation Solver for High-Dimensional Derivative Pricing

no code implementations24 Jul 2019 Jian Liang, Zhe Xu, Peter Li

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

no code implementations CVPR 2019 Jian Liang, Ran He, Zhenan Sun, Tieniu Tan

Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains.

Domain Generalization Face Recognition +1

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets

2 code implementations ACL 2019 Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

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.

Selection bias

Model-Protected Multi-Task Learning

1 code implementation18 Sep 2018 Jian Liang, Ziqi Liu, Jiayu Zhou, Xiaoqian Jiang, Chang-Shui Zhang, Fei Wang

Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together.

Multi-Task Learning Privacy Preserving

Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach

1 code implementation CVPR 2018 Lingxiao He, Jian Liang, Haiqing Li, Zhenan Sun

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.

Dictionary Learning Person Re-Identification

Robust Localized Multi-view Subspace Clustering

no code implementations22 May 2017 Yanbo Fan, Jian Liang, Ran He, Bao-Gang Hu, Siwei Lyu

In multi-view clustering, different views may have different confidence levels when learning a consensus representation.

Multi-view Subspace Clustering

Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm

no code implementations28 Feb 2017 Ziang Yan, Jian Liang, Weishen Pan, Jin Li, Chang-Shui Zhang

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.

object-detection Object Detection +1

Self-Paced Learning: an Implicit Regularization Perspective

no code implementations1 Jun 2016 Yanbo Fan, Ran He, Jian Liang, Bao-Gang Hu

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.

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