Search Results for author: Zhen Cheng

Found 16 papers, 8 papers with code

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.

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

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

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.

Adaptive Sparse Pairwise Loss for Object Re-Identification

1 code implementation CVPR 2023 Xiao Zhou, Yujie Zhong, Zhen Cheng, Fan Liang, Lin Ma

To address this problem, we propose a novel loss paradigm termed Sparse Pairwise (SP) loss that only leverages few appropriate pairs for each class in a mini-batch, and empirically demonstrate that it is sufficient for the ReID tasks.


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

Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables

1 code implementation25 Mar 2023 Jiacheng Li, Chang Chen, Zhen Cheng, Zhiwei Xiong

However, the size of a single LUT grows exponentially with the increase of its indexing capacity, which restricts its receptive field and thus the performance.

Demosaicking Denoising +1

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.

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 Real World HDRTV Reconstruction: A Data Synthesis-based Approach

no code implementations6 Nov 2022 Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, Chang Chen, Zhiwei Xiong

To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions.

Tone Mapping

Degradation-agnostic Correspondence from Resolution-asymmetric Stereo

no code implementations CVPR 2022 Xihao Chen, Zhiwei Xiong, Zhen Cheng, Jiayong Peng, Yueyi Zhang, Zheng-Jun Zha

Interestingly, we find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features.

Stereo Matching

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

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

Light Field Super-Resolution With Zero-Shot Learning

no code implementations CVPR 2021 Zhen Cheng, Zhiwei Xiong, Chang Chen, Dong Liu, Zheng-Jun Zha

To fill this gap, we propose a zero-shot learning framework for light field SR, which learns a mapping to super-resolve the reference view with examples extracted solely from the input low-resolution light field itself.

Super-Resolution Zero-Shot Learning

Space-Time Distillation for Video Super-Resolution

no code implementations CVPR 2021 Zeyu Xiao, Xueyang Fu, Jie Huang, Zhen Cheng, Zhiwei Xiong

In this paper, we aim to improve the performance of compact VSR networks without changing their original architectures, through a knowledge distillation approach that transfers knowledge from a complicated VSR network to a compact one.

Knowledge Distillation Video Super-Resolution

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