中文
相关论文

相关论文: HamBR: Active Decision Boundary Restoration Based …

200 篇论文

Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes, and poses a severe threat to the…

计算机视觉与模式识别 · 计算机科学 2022-01-28 Wei Zhu , Zihe Zheng , Haitian Zheng , Hanjia Lyu , Jiebo Luo

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

计算机视觉与模式识别 · 计算机科学 2015-04-16 Scott Reed , Honglak Lee , Dragomir Anguelov , Christian Szegedy , Dumitru Erhan , Andrew Rabinovich

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

机器学习 · 计算机科学 2025-10-30 Kuan Zhang , Chengliang Chai , Jingzhe Xu , Chi Zhang , Han Han , Ye Yuan , Guoren Wang , Lei Cao

Face recognition has made tremendous progress in recent years due to the advances in loss functions and the explosive growth in training sets size. A properly designed loss is seen as key to extract discriminative features for…

计算机视觉与模式识别 · 计算机科学 2022-10-11 Shijie Wu , Xun Gong

Deep neural networks have great representation power, but typically require large numbers of training examples. This motivates deep active learning methods that can significantly reduce the amount of labeled training data. Empirical…

机器学习 · 计算机科学 2026-01-01 Yinglun Zhu , Robert Nowak

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…

机器学习 · 计算机科学 2025-02-12 Mengyang Li

Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in annotation time and in the annotators' expertise. Existing…

图像与视频处理 · 电气工程与系统科学 2023-08-08 Jiachen Yao , Yikai Zhang , Songzhu Zheng , Mayank Goswami , Prateek Prasanna , Chao Chen

While Hamiltonian mechanics provides a powerful inductive bias for neural networks modeling dynamical systems, Hamiltonian Neural Networks and their variants often fail to capture complex temporal dynamics spanning multiple timescales. This…

机器学习 · 计算机科学 2026-03-17 Yaojun Li , Yulong Yang , Christine Allen-Blanchette

Graph neural networks (GNNs) have been widely used in various graph machine learning scenarios. Existing literature primarily assumes well-annotated training graphs, while the reliability of labels is not guaranteed in real-world scenarios.…

机器学习 · 计算机科学 2026-01-27 Yusheng Zhao , Jiaye Xie , Qixin Zhang , Weizhi Zhang , Xiao Luo , Zhiping Xiao , Philip S. Yu , Ming Zhang

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning \mbox{methods}…

机器学习 · 计算机科学 2022-03-18 Qizhou Wang , Bo Han , Tongliang Liu , Gang Niu , Jian Yang , Chen Gong

Active Learning (AL) aims to reduce annotation costs by strategically selecting the most informative samples for labeling. However, most active learning methods struggle in the low-budget regime where only a few labeled examples are…

机器学习 · 计算机科学 2025-04-08 Netta Shafir , Guy Hacohen , Daphna Weinshall

Active learning (AL) techniques reduce labeling costs for training neural machine translation (NMT) models by selecting smaller representative subsets from unlabeled data for annotation. Diversity sampling techniques select heterogeneous…

计算与语言 · 计算机科学 2024-12-19 Abdul Hameed Azeemi , Ihsan Ayyub Qazi , Agha Ali Raza

Imperfect labels are ubiquitous in real-world datasets and seriously harm the model performance. Several recent effective methods for handling noisy labels have two key steps: 1) dividing samples into cleanly labeled and wrongly labeled…

计算机视觉与模式识别 · 计算机科学 2022-02-01 Wenkai Chen , Chuang Zhu , Yi Chen , Mengting Li , Tiejun Huang

Ensuring the robustness of deep neural networks against adversarial attacks remains a fundamental challenge in computer vision. While adversarial training (AT) has emerged as a promising defense strategy, our analysis reveals a critical…

计算机视觉与模式识别 · 计算机科学 2025-01-14 Kejia Zhang , Juanjuan Weng , Yuanzheng Cai , Zhiming Luo , Shaozi Li

We develop the first active learning method for contextual linear optimization. Specifically, we introduce a label acquisition algorithm that sequentially decides whether to request the ``labels'' of feature samples from an unlabeled data…

机器学习 · 计算机科学 2025-01-31 Mo Liu , Paul Grigas , Heyuan Liu , Zuo-Jun Max Shen

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision…

计算与语言 · 计算机科学 2025-07-23 Hui Xiang , Jinqiao Shi , Ting Zhang , Xiaojie Zhao , Yong Liu , Yong Ma

In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels. Existing PML methods typically design…

计算机视觉与模式识别 · 计算机科学 2024-05-07 Feng Sun , Ming-Kun Xie , Sheng-Jun Huang

Random label noises (or observational noises) widely exist in practical machine learning settings. While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the…

机器学习 · 计算机科学 2023-04-04 Haoyi Xiong , Xuhong Li , Boyang Yu , Zhanxing Zhu , Dongrui Wu , Dejing Dou

Classification models are a fundamental component of physical-asset management technologies such as structural health monitoring (SHM) systems and digital twins. Previous work introduced risk-based active learning, an online approach for…

机器学习 · 计算机科学 2022-07-13 Aidan J. Hughes , Lawrence A. Bull , Paul Gardner , Nikolaos Dervilis , Keith Worden

In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is…

计算机视觉与模式识别 · 计算机科学 2024-04-29 Yanbiao Ma , Licheng Jiao , Fang Liu , Lingling Li , Shuyuan Yang , Xu Liu