no code implementations • 14 Apr 2024 • Yongqi Xu, Yujian Lee, Rong Zou, Yiqun Zhang, Yiu-ming Cheung
That is, the imbalanced degree of clusters varies in different streaming data chunks, leading to corruption in either the accuracy or the efficiency of streaming data analysis based on existing clustering methods.
no code implementations • 3 Apr 2024 • Weichao Lan, Yiu-ming Cheung, Qing Xu, Buhua Liu, Zhikai Hu, Mengke Li, Zhenghua Chen
In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model.
no code implementations • 11 Mar 2024 • Jintao Huang, Yiu-ming Cheung
PLL-OOD significantly enhances model adaptability and accuracy by merging self-supervised learning with partial label loss and pioneering the Partial-Energy (PE) score for OOD detection.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +2
1 code implementation • 20 Dec 2023 • Yang Lu, Lin Chen, Yonggang Zhang, Yiliang Zhang, Bo Han, Yiu-ming Cheung, Hanzi Wang
The model trained on noisy labels serves as a `bad teacher' in knowledge distillation, aiming to decrease the risk of providing incorrect information.
no code implementations • 29 Nov 2023 • Xiaoge Zhang, Xiao-Lin Wang, Fenglei Fan, Yiu-ming Cheung, Indranil Bose
Regarding the loss function, both intermediate and leaf nodes in the DAG graph are treated as target outputs during CINN training so as to drive co-learning of causal relationships among different types of nodes.
1 code implementation • 12 Jun 2023 • Mengke Li, Zhikai Hu, Yang Lu, Weichao Lan, Yiu-ming Cheung, Hui Huang
To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T).
1 code implementation • CVPR 2022 • Mengke Li, Yiu-ming Cheung, Yang Lu
It is unfavorable for training on balanced data, but can be utilized to adjust the validity of the samples in long-tailed data, thereby solving the distorted embedding space of long-tailed problems.
Ranked #13 on Long-tail Learning on CIFAR-10-LT (ρ=100)
1 code implementation • 18 May 2023 • Mengke Li, Yiu-ming Cheung, Yang Lu, Zhikai Hu, Weichao Lan, Hui Huang
Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead.
1 code implementation • IEEE International Conference on Multimedia and Expo (ICME) 2022 • Mengke Li, Yiu-ming Cheung, Juyong Jiang
Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model.
Ranked #14 on Long-tail Learning on CIFAR-10-LT (ρ=100)
1 code implementation • CVPR 2023 • Yan Jin, Mengke Li, Yang Lu, Yiu-ming Cheung, Hanzi Wang
To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution.
no code implementations • 4 Mar 2023 • Xinyi Shang, Gang Huang, Yang Lu, Jian Lou, Bo Han, Yiu-ming Cheung, Hanzi Wang
Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data.
no code implementations • 3 Feb 2023 • Hongmin Cai, Fei Qi, Junyu Li, Yu Hu, Yue Zhang, Yiu-ming Cheung, Bin Hu
Conventional clustering methods based on pairwise affinity usually suffer from the concentration effect while processing huge dimensional features yet low sample sizes data, resulting in inaccuracy to encode the sample proximity and suboptimal performance in clustering.
1 code implementation • ICCV 2023 • Yang Lu, Yiliang Zhang, Bo Han, Yiu-ming Cheung, Hanzi Wang
In this case, it is hard to distinguish clean samples from noisy samples on the intrinsic tail classes with the unknown intrinsic class distribution.
no code implementations • 3 May 2022 • Weichao Lan, Yiu-ming Cheung, Juyong Jiang
To this end, this paper presents a new method termed TissueNet, which directly constructs compact neural networks with fewer weight parameters by independently stacking designed basic units, without requiring additional judgement criteria anymore.
1 code implementation • 30 Apr 2022 • Xinyi Shang, Yang Lu, Yiu-ming Cheung, Hanzi Wang
Federated learning provides a privacy guarantee for generating good deep learning models on distributed clients with different kinds of data.
1 code implementation • 3 Mar 2022 • Yiu-ming Cheung, Juyong Jiang, Feng Yu, Jian Lou
Despite enormous research interest and rapid application of federated learning (FL) to various areas, existing studies mostly focus on supervised federated learning under the horizontally partitioned local dataset setting.
1 code implementation • 15 May 2021 • Xin Liu, Xingzhi Wang, Yiu-ming Cheung
To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data so as to minimize the quantization loss of mapping such data to hamming space, and propose an efficient Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval.
no code implementations • Journal - IEEE Transactions on Neural Networks and Learning Systems 2021 • Cuie Yang, Yiu-ming Cheung, Jinliang Ding, Kay Chen Tan
Then, a domain-wise weighted ensemble is introduced to combine the source and target models to select useful knowledge of each domain.
no code implementations • 19 Oct 2019 • Weizhen Hu, Min Jiang, Xing Gao, Kay Chen Tan, Yiu-ming Cheung
The main feature of the Dynamic Multi-objective Optimization Problems (DMOPs) is that optimization objective functions will change with times or environments.
no code implementations • 29 Jan 2019 • Yang Lu, Yiu-ming Cheung, Yuan Yan Tang
To the best of our knowledge, there is no any measurement about the extent of influence of class imbalance on the classification performance of imbalanced data.
1 code implementation • 4 May 2018 • Xin Liu, Zhikai Hu, Haibin Ling, Yiu-ming Cheung
More specifically, MTFH exploits an efficient objective function to flexibly learn the modality-specific hash codes with different length settings, while synchronously learning two semantic correlation matrices to semantically correlate the different hash representations for heterogeneous data comparable.
no code implementations • CVPR 2016 • Haifei Huang, HUI ZHANG, Yiu-ming Cheung
In this paper, we address the problem of homography estimation from two separate ellipses.
no code implementations • 28 Aug 2015 • Zihao Wang, Yiu-ming Cheung
In this paper, we present a novel regularization method based on a clustering algorithm which is able to classify the parameters into different groups.
no code implementations • CVPR 2015 • Haifei Huang, HUI ZHANG, Yiu-ming Cheung
In this paper, we explore the properties of the common self-polar triangle, when the two conics happen to be concentric circles.