Search Results for author: Weiping Wang

Found 73 papers, 30 papers with code

Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection

1 code implementation COLING 2022 Rui Liu, Zheng Lin, Huishan Ji, Jiangnan Li, Peng Fu, Weiping Wang

Despite the significant progress on this task, it is extremely time-consuming and budget-unfriendly to collect sufficient high-quality labeled data for every new target under fully-supervised learning, whereas unlabeled data can be collected easier.

Contrastive Learning Stance Detection

TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation

1 code implementation COLING 2022 Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie zhou

The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation.

Dialogue Generation Knowledge Distillation +1

Combo of Thinking and Observing for Outside-Knowledge VQA

1 code implementation10 May 2023 Qingyi Si, Yuchen Mo, Zheng Lin, Huishan Ji, Weiping Wang

Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features.

Question Answering Visual Question Answering

Robust Neural Architecture Search

no code implementations6 Apr 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

Neural Architectures Search (NAS) becomes more and more popular over these years.

Image Classification Neural Architecture Search

Operation-level Progressive Differentiable Architecture Search

1 code implementation11 Feb 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.

Neural Architecture Search

Improving Differentiable Architecture Search via Self-Distillation

no code implementations11 Feb 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.

Neural Architecture Search

UATVR: Uncertainty-Adaptive Text-Video Retrieval

no code implementations16 Jan 2023 Bo Fang, Wenhao Wu, Chang Liu, Yu Zhou, Min Yang, Yuxin Song, Fu Li, Weiping Wang, Xiangyang Ji, Wanli Ouyang

In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.

Retrieval Semantic correspondence +1

Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning

no code implementations2 Nov 2022 Yifei Zhang, Chang Liu, Yu Zhou, Weiping Wang, Qixiang Ye, Xiangyang Ji

In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i. e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion.

Self-Supervised Learning

COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models

1 code implementation27 Oct 2022 Bowen Shen, Zheng Lin, Yuanxin Liu, Zhengxiao Liu, Lei Wang, Weiping Wang

Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.

Model Compression

Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering

no code implementations26 Oct 2022 Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu, Weiping Wang

To facilitate the application of VLP to VQA tasks, it is imperative to jointly study VLP compression and OOD robustness, which, however, has not yet been explored.

Question Answering Visual Question Answering

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension

no code implementations26 Oct 2022 Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie zhou

Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances.

Reading Comprehension

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection

1 code implementation21 Oct 2022 Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie zhou

We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response.

Dialogue Generation Emotion Recognition +2

Joint Plasticity Learning for Camera Incremental Person Re-Identification

no code implementations17 Oct 2022 Zexian Yang, Dayan Wu, Bo Li, Weiping Wang

This is challenging as the new data only have local supervision in new cameras with no access to the old data due to privacy issues, and they may also contain persons seen by previous cameras.

Incremental Learning Person Re-Identification

A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models

1 code implementation11 Oct 2022 Yuanxin Liu, Fandong Meng, Zheng Lin, Jiangnan Li, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.

Natural Language Understanding

Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA

1 code implementation10 Oct 2022 Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.

Question Answering Visual Question Answering

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning

1 code implementation10 Oct 2022 Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

However, these models reveal a trade-off that the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data (which is dominated by the biased samples).

Contrastive Learning Question Answering +1

Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM

no code implementations6 Jun 2022 Yuzhe Li, Yong liu, Bo Li, Weiping Wang, Nan Liu

In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.

Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training

1 code implementation NAACL 2022 Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou

Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.

Transfer Learning

Sharper Utility Bounds for Differentially Private Models

no code implementations22 Apr 2022 Yilin Kang, Yong liu, Jian Li, Weiping Wang

In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.

Stability and Generalization of Differentially Private Minimax Problems

no code implementations11 Apr 2022 Yilin Kang, Yong liu, Jian Li, Weiping Wang

To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

1 code implementation15 Dec 2021 Xiaohua Chen, Yucan Zhou, Dayan Wu, Wanqian Zhang, Yu Zhou, Bo Li, Weiping Wang

Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances.

Data Augmentation Long-tail Learning

TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation

1 code implementation25 Oct 2021 Wei Wang, Yu Zhou, Jiahao Lv, Dayan Wu, Guoqing Zhao, Ning Jiang, Weiping Wang

The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem.

Scene Text Detection Scene Text Recognition

Dense Semantic Contrast for Self-Supervised Visual Representation Learning

no code implementations16 Sep 2021 Xiaoni Li, Yu Zhou, Yifei Zhang, Aoting Zhang, Wei Wang, Ning Jiang, Haiying Wu, Weiping Wang

Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods.

Contrastive Learning Instance Segmentation +4

PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition

1 code implementation9 Sep 2021 Zhi Qiao, Yu Zhou, Jin Wei, Wei Wang, Yuan Zhang, Ning Jiang, Hongbin Wang, Weiping Wang

In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency.

Scene Text Recognition

Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection

no code implementations8 Sep 2021 Xugong Qin, Yu Zhou, Youhui Guo, Dayan Wu, Zhihong Tian, Ning Jiang, Hongbin Wang, Weiping Wang

We propose to use an MLP decoder instead of the "deconv-conv" decoder in the mask head, which alleviates the issue and promotes robustness significantly.

Instance Segmentation object-detection +3

Video 3D Sampling for Self-supervised Representation Learning

no code implementations8 Jul 2021 Wei Li, Dezhao Luo, Bo Fang, Yu Zhou, Weiping Wang

As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target.

Action Recognition Representation Learning +2

Multi-View Correlation Distillation for Incremental Object Detection

no code implementations5 Jul 2021 Dongbao Yang, Yu Zhou, Weiping Wang

Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data.

object-detection Object Detection

MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification

no code implementations2 Jul 2021 Xiaoni Li, Yucan Zhou, Yu Zhou, Weiping Wang

Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes.

Classification Image Classification

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

1 code implementation ACL 2021 Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie zhou

In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.

Knowledge Distillation

Check It Again: Progressive Visual Question Answering via Visual Entailment

1 code implementation8 Jun 2021 Qingyi Si, Zheng Lin, Mingyu Zheng, Peng Fu, Weiping Wang

Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.

Question Answering Visual Entailment +1

Exploring Instance Relations for Unsupervised Feature Embedding

1 code implementation7 May 2021 Yifei Zhang, Yu Zhou, Weiping Wang

Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations.

Contrastive Learning Image Classification +1

Towards Sharper Utility Bounds for Differentially Private Pairwise Learning

no code implementations7 May 2021 Yilin Kang, Yong liu, Jian Li, Weiping Wang

Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.

Rescuing Deep Hashing from Dead Bits Problem

no code implementations1 Feb 2021 Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang

The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods.

Image Retrieval Quantization +1

Deep Learning for Instance Retrieval: A Survey

no code implementations27 Jan 2021 Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.

Content-Based Image Retrieval Instance Search +1

A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation

1 code implementation29 Dec 2020 Jiangnan Li, Zheng Lin, Peng Fu, Qingyi Si, Weiping Wang

It can be regarded as a personalized and interactive emotion recognition task, which is supposed to consider not only the semantic information of text but also the influences from speakers.

Emotion Recognition in Conversation

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

1 code implementation3 Dec 2020 Qingyi Si, Yuanxin Liu, Peng Fu, Zheng Lin, Jiangnan Li, Weiping Wang

A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage.

Intent Detection Multi-Task Learning +1

Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection

no code implementations Findings of the Association for Computational Linguistics 2020 Hongliang Pan, Zheng Lin, Peng Fu, Yatao Qi, Weiping Wang

Inspired by this, we propose a BERT architecture-based model, which concentrates on both intra and inter-modality incongruity for multi-modal sarcasm detection.

Sarcasm Detection

Gaussian Constrained Attention Network for Scene Text Recognition

1 code implementation19 Oct 2020 Zhi Qiao, Xugong Qin, Yu Zhou, Fei Yang, Weiping Wang

In this paper, we propose Gaussian Constrained Attention Network to deal with this problem.

Scene Text Recognition

New Ideas and Trends in Deep Multimodal Content Understanding: A Review

no code implementations16 Oct 2020 Wei Chen, Weiping Wang, Li Liu, Michael S. Lew

The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.

Cross-Modal Retrieval Image Captioning +5

On the Exploration of Incremental Learning for Fine-grained Image Retrieval

1 code implementation15 Oct 2020 Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker, Michael Lew

On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.

Image Retrieval Incremental Learning +1

Dirichlet type extensions of Euler sums

no code implementations12 Sep 2020 Weiping Wang, Ce Xu

In this paper, we study the alternating Euler $T$-sums and $\S$-sums, which are infinite series involving (alternating) odd harmonic numbers, and have similar forms and close relations to the Dirichlet beta functions.

Number Theory

Two-Level Residual Distillation based Triple Network for Incremental Object Detection

no code implementations27 Jul 2020 Dongbao Yang, Yu Zhou, Dayan Wu, Can Ma, Fei Yang, Weiping Wang

Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.

Incremental Learning object-detection +2

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification

no code implementations13 Jul 2020 Yucan Zhou, Yu Wang, Jianfei Cai, Yu Zhou, QinGhua Hu, Weiping Wang

Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.

General Classification Meta-Learning

FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection

no code implementations10 Jul 2020 Xugong Qin, Yu Zhou, Dayan Wu, Yinliang Yue, Weiping Wang

Accurate detection of multi-oriented text with large variations of scales, orientations, and aspect ratios is of great significance.

Multi-Oriented Scene Text Detection

Progressive Cluster Purification for Unsupervised Feature Learning

1 code implementation6 Jul 2020 Yifei Zhang, Chang Liu, Yu Zhou, Wei Wang, Weiping Wang, Qixiang Ye

In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.


Neural Architecture Optimization with Graph VAE

no code implementations18 Jun 2020 Jian Li, Yong liu, Jiankun Liu, Weiping Wang

The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.

Neural Architecture Search

Self-Training for Domain Adaptive Scene Text Detection

no code implementations23 May 2020 Yudi Chen, Wei Wang, Yu Zhou, Fei Yang, Dongbao Yang, Weiping Wang

To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.

Image to Video Generation Scene Text Detection

Keyphrase Prediction With Pre-trained Language Model

no code implementations22 Apr 2020 Rui Liu, Zheng Lin, Weiping Wang

Considering the different characteristics of extractive and generative methods, we propose to divide the keyphrase prediction into two subtasks, i. e., present keyphrase extraction (PKE) and absent keyphrase generation (AKG), to fully exploit their respective advantages.

Keyphrase Extraction Keyphrase Generation +1

Nearly Optimal Clustering Risk Bounds for Kernel K-Means

no code implementations9 Mar 2020 Yong Liu, Lizhong Ding, Weiping Wang

In this paper, we study the statistical properties of kernel $k$-means and obtain a nearly optimal excess clustering risk bound, substantially improving the state-of-art bounds in the existing clustering risk analyses.

Theoretical Analysis of Divide-and-Conquer ERM: Beyond Square Loss and RKHS

no code implementations9 Mar 2020 Yong Liu, Lizhong Ding, Weiping Wang

However, the studies on learning theory for general loss functions and hypothesis spaces remain limited.

Learning Theory

Convolutional Spectral Kernel Learning

no code implementations28 Feb 2020 Jian Li, Yong liu, Weiping Wang

Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics.

Data Heterogeneity Differential Privacy: From Theory to Algorithm

no code implementations20 Feb 2020 Yilin Kang, Jian Li, Yong liu, Weiping Wang

Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP).

BIG-bench Machine Learning

Input Perturbation: A New Paradigm between Central and Local Differential Privacy

1 code implementation20 Feb 2020 Yilin Kang, Yong liu, Ben Niu, Xin-Yi Tong, Likun Zhang, Weiping Wang

By adding noise to the original training data and training with the `perturbed data', we achieve ($\epsilon$,$\delta$)-differential privacy on the final model, along with some kind of privacy on the original data.

Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning

1 code implementation2 Jan 2020 Dezhao Luo, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, Weiping Wang

As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.

Representation Learning Retrieval +4

Weighted Distributed Differential Privacy ERM: Convex and Non-convex

no code implementations23 Oct 2019 Yilin Kang, Yong liu, Weiping Wang

By detailed theoretical analysis, we show that in distributed setting, the noise bound and the excess empirical risk bound can be improved by considering different weights held by multiple parties.

Automated Spectral Kernel Learning

1 code implementation11 Sep 2019 Jian Li, Yong liu, Weiping Wang

The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks.

Semi-supervised Vector-valued Learning: From Theory to Algorithm

1 code implementation11 Sep 2019 Jian Li, Yong liu, Weiping Wang

Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e. g. multi-label learning and multi-class classification.

Multi-class Classification Multi-Label Learning

Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning

no code implementations27 Aug 2019 Xugong Qin, Yu Zhou, Dongbao Yang, Weiping Wang

The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.

Curved Text Detection Weakly-supervised Learning

Towards Sharp Analysis for Distributed Learning with Random Features

1 code implementation7 Jun 2019 Jian Li, Yong liu, Weiping Wang

In this paper, using refined proof techniques, we first extend the optimal rates for distributed learning with random features to the non-attainable case.

Efficient Cross-Validation for Semi-Supervised Learning

no code implementations13 Feb 2019 Yong Liu, Jian Li, Guangjun Wu, Lizhong Ding, Weiping Wang

In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF).

Model Selection

Max-Diversity Distributed Learning: Theory and Algorithms

no code implementations19 Dec 2018 Yong Liu, Jian Li, Weiping Wang

We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning.

Learning Theory

Multi-Class Learning: From Theory to Algorithm

no code implementations NeurIPS 2018 Jian Li, Yong liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang

In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.

Classification General Classification +1

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