Search Results for author: Xu-Yao Zhang

Found 34 papers, 14 papers with code

Towards Trustworthy Dataset Distillation

1 code implementation18 Jul 2023 Shijie Ma, Fei Zhu, Zhen Cheng, Xu-Yao Zhang

By distilling both InD samples and outliers, the condensed datasets are capable to train models competent in both InD classification and OOD detection.

Prototype Augmentation and Self-Supervision for Incremental Learning

1 code implementation CVPR 2021 Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, Cheng-Lin Liu

Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally.

Incremental Learning Self-Supervised Learning

Class-Incremental Learning via Dual Augmentation

2 code implementations NeurIPS 2021 Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

Deep learning systems typically suffer from catastrophic forgetting of past knowledge when acquiring new skills continually.

Class Incremental Learning Incremental Learning

Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network

1 code implementation14 Apr 2021 Guo-Wang Xie, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu

As camera-based documents are increasingly used, the rectification of distorted document images becomes a need to improve the recognition performance.

Document Dewarping with Control Points

1 code implementation20 Mar 2022 Guo-Wang Xie, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu

In this paper, we propose a simple yet effective approach to rectify distorted document image by estimating control points and reference points.

Optical Character Recognition (OCR)

Drawing and Recognizing Chinese Characters with Recurrent Neural Network

1 code implementation21 Jun 2016 Xu-Yao Zhang, Fei Yin, Yan-Ming Zhang, Cheng-Lin Liu, Yoshua Bengio

In this paper, we propose a framework by using the recurrent neural network (RNN) as both a discriminative model for recognizing Chinese characters and a generative model for drawing (generating) Chinese characters.

Handwriting Recognition

Rethinking Confidence Calibration for Failure Prediction

1 code implementation6 Mar 2023 Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

We investigate this problem and reveal that popular confidence calibration methods often lead to worse confidence separation between correct and incorrect samples, making it more difficult to decide whether to trust a prediction or not.

Revisiting Confidence Estimation: Towards Reliable Failure Prediction

1 code implementation5 Mar 2024 Fei Zhu, Xu-Yao Zhang, Zhen Cheng, Cheng-Lin Liu

Reliable confidence estimation is a challenging yet fundamental requirement in many risk-sensitive applications.

OpenMix: Exploring Outlier Samples for Misclassification Detection

1 code implementation CVPR 2023 Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications.

World Knowledge

Dynamics-Aware Loss for Learning with Label Noise

1 code implementation21 Mar 2023 Xiu-Chuan Li, Xiaobo Xia, Fei Zhu, Tongliang Liu, Xu-Yao Zhang, Cheng-Lin Liu

Label noise poses a serious threat to deep neural networks (DNNs).

Active Generalized Category Discovery

1 code implementation7 Mar 2024 Shijie Ma, Fei Zhu, Zhun Zhong, Xu-Yao Zhang, Cheng-Lin Liu

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes.

Active Learning imbalanced classification +1

Stochastic Conjugate Gradient Algorithm with Variance Reduction

1 code implementation27 Oct 2017 Xiao-Bo Jin, Xu-Yao Zhang, Kai-Zhu Huang, Guang-Gang Geng

Conjugate gradient (CG) methods are a class of important methods for solving linear equations and nonlinear optimization problems.

Computational Efficiency

Unified Classification and Rejection: A One-versus-All Framework

1 code implementation22 Nov 2023 Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes.

Binary Classification Classification +1

SCAN: Sliding Convolutional Attention Network for Scene Text Recognition

no code implementations2 Jun 2018 Yi-Chao Wu, Fei Yin, Xu-Yao Zhang, Li Liu, Cheng-Lin Liu

Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications.

Scene Text Recognition

Scene Text Recognition with Sliding Convolutional Character Models

no code implementations6 Sep 2017 Fei Yin, Yi-Chao Wu, Xu-Yao Zhang, Cheng-Lin Liu

In this paper, we investigate the intrinsic characteristics of text recognition, and inspired by human cognition mechanisms in reading texts, we propose a scene text recognition method with character models on convolutional feature map.

Scene Text Recognition

Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark

no code implementations18 Jun 2016 Xu-Yao Zhang, Yoshua Bengio, Cheng-Lin Liu

Furthermore, although directMap+convNet can achieve the best results and surpass human-level performance, we show that writer adaptation in this case is still effective.

Data Augmentation Offline Handwritten Chinese Character Recognition

Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation

no code implementations29 Jan 2016 Guo-Sen Xie, Xu-Yao Zhang, Shuicheng Yan, Cheng-Lin Liu

Learned from a large-scale training dataset, CNN features are much more discriminative and accurate than the hand-crafted features.

Clustering Domain Adaptation +1

Predictive Ensemble Learning with Application to Scene Text Detection

no code implementations12 May 2019 Danlu Chen, Xu-Yao Zhang, Wei zhang, Yao Lu, Xiuli Li, Tao Mei

Taking scene text detection as the application, where no suitable ensemble learning strategy exists, PEL can significantly improve the performance, compared to either individual state-of-the-art models, or the fusion of multiple models by non-maximum suppression.

Classification Ensemble Learning +5

Towards Robust Pattern Recognition: A Review

no code implementations12 Jun 2020 Xu-Yao Zhang, Cheng-Lin Liu, Ching Y. Suen

The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance.

Misclassification Detection via Class Augmentation

no code implementations1 Jan 2021 Fei Zhu, Xu-Yao Zhang, Chuang Wang, Cheng-Lin Liu

In spite of the simplicity, extensive experiments demonstrate that the misclassification detection performance of DNNs can be significantly improved by seeing more generated pseudo-classes during training.

Few-Shot Learning

Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm

no code implementations1 Dec 2020 Mengbiao Zhao, Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu

We propose an Expectation-Maximization (EM) based weakly-supervised learning framework to train an accurate arbitrary-shaped text detector using only a small amount of polygon-level annotated data combined with a large amount of weakly annotated data.

Text Detection Weakly-supervised Learning

Semantic-Aware Video Text Detection

no code implementations CVPR 2021 Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu

To overcome the lack of character-level annotations, we propose a novel weakly-supervised character center detection module, which only uses word-level annotated real images to generate character-level labels.

Text Detection

Delving into Feature Space: Improving Adversarial Robustness by Feature Spectral Regularization

no code implementations29 Sep 2021 Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu

Comprehensive experiments demonstrate that FSR is effective to alleviate the dominance of larger eigenvalues and improve adversarial robustness on different datasets.

Adversarial Robustness Attribute

Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks

no code implementations14 Jan 2022 Yuqi Wang, Xu-Yao Zhang, Cheng-Lin Liu, Zhaoxiang Zhang

Moreover, through experiments we show that discrete language representation has several advantages compared with continuous feature representation, from the aspects of interpretability, generalization, and robustness.

A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies

no code implementations26 Mar 2022 Zhuang Qian, Kaizhu Huang, Qiu-Feng Wang, Xu-Yao Zhang

In this paper, we present a comprehensive survey trying to offer a systematic and structured investigation on robust adversarial training in pattern recognition.

Adversarial Attack

Proxy Graph Matching with Proximal Matching Networks

no code implementations AAAI 2021 Haoru Tan, Chuang Wang, Sitong Wu, Tie-Qiang Wang, Xu-Yao Zhang, Cheng-Lin Liu

It consists of three parts: a graph neural network to generate a high-level local feature, an attention-based module to normalize the rotational transform, and a global feature matching module based on proximal optimization.

Graph Matching

Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection

no code implementations2 Mar 2023 Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu

Detecting Out-of-distribution (OOD) inputs have been a critical issue for neural networks in the open world.

Out-of-Distribution Detection

Towards Reliable Domain Generalization: A New Dataset and Evaluations

no code implementations12 Sep 2023 Jiao Zhang, Xu-Yao Zhang, Cheng-Lin Liu

We advocate that researchers in the DG community refer to dynamic performance of methods for more comprehensive and reliable evaluation.

Domain Generalization

Federated Class-Incremental Learning with Prototype Guided Transformer

no code implementations4 Jan 2024 Haiyang Guo, Fei Zhu, Wenzhuo LIU, Xu-Yao Zhang, Cheng-Lin Liu

On the other hand, our approach utilizes a pre-trained model as the backbone and utilizes LoRA to fine-tune with a tiny amount of parameters when learning new classes.

Class Incremental Learning Federated Learning +1

Open-world Machine Learning: A Review and New Outlooks

no code implementations4 Mar 2024 Fei Zhu, Shijie Ma, Zhen Cheng, Xu-Yao Zhang, Zhaoxiang Zhang, Cheng-Lin Liu

This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm, to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.

Class Incremental Learning Incremental Learning +1

Ensemble Quadratic Assignment Network for Graph Matching

no code implementations11 Mar 2024 Haoru Tan, Chuang Wang, Sitong Wu, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu

In this paper, we propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.

3D Shape Classification Graph Matching

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