English
Related papers

Related papers: MixMOOD: A systematic approach to class distributi…

200 papers

Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Chaohua Li , Enhao Zhang , Chuanxing Geng , Songcan Chen

Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Dongdong Meng , Sheng Li , Hao Wu , Guoping Wang , Xueqing Yan

How can we automatically select an out-of-distribution (OOD) detection model for various underlying tasks? This is crucial for maintaining the reliability of open-world applications by identifying data distribution shifts, particularly in…

Machine Learning · Computer Science 2025-03-03 Yuehan Qin , Yichi Zhang , Yi Nian , Xueying Ding , Yue Zhao

While supervised deep learning has achieved great success in a range of applications, relatively little work has studied the discovery of knowledge from unlabeled data. In this paper, we propose an unsupervised deep learning framework to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Jinghua Wang , Jianmin Jiang

Out-of-distribution (OOD) detection, which aims to distinguish unknown classes from known classes, has received increasing attention recently. A main challenge within is the unavailable of samples from the unknown classes in the training…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Mingle Xu , Jaehwan Lee , Sook Yoon , Dong Sun Park

Open-set node classification (OSNC) allows unlabeled test data to contain novel classes previously unseen in the labeled data. The goal is to classify in-distribution (ID) nodes into corresponding known classes and reject…

Social and Information Networks · Computer Science 2026-03-24 Junwei Gong , Xiao Shen , Zhihao Chen , Shirui Pan , Xiao Wang , Xi Zhou

Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation,…

Machine Learning · Computer Science 2023-11-06 Wei-Chao Cheng , Tan-Ha Mai , Hsuan-Tien Lin

For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face…

Computer Vision and Pattern Recognition · Computer Science 2024-01-10 Kuo Yang , Duo Li , Menghan Hu , Guangtao Zhai , Xiaokang Yang , Xiao-Ping Zhang

Since deep learning models have been implemented in many commercial applications, it is important to detect out-of-distribution (OOD) inputs correctly to maintain the performance of the models, ensure the quality of the collected data, and…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Qing Yu , Kiyoharu Aizawa

Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world. The vast majority of OOD detection methods are driven by a single modality (e.g., either vision or language), leaving the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Yifei Ming , Ziyang Cai , Jiuxiang Gu , Yiyou Sun , Wei Li , Yixuan Li

In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with…

Sound · Computer Science 2020-02-13 Turab Iqbal , Yin Cao , Qiuqiang Kong , Mark D. Plumbley , Wenwu Wang

Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the…

Machine Learning · Computer Science 2024-09-20 Jeng-Lin Li , Ming-Ching Chang , Wei-Chao Chen

Compared to supervised learning, semi-supervised learning reduces the dependence of deep learning on a large number of labeled samples. In this work, we use a small number of labeled samples and perform data augmentation on unlabeled…

Machine Learning · Computer Science 2020-01-14 Qiuyu Zhu , Tiantian Li

While much of recent study in semi-supervised learning (SSL) has achieved strong performance on single-label classification problems, an equally important yet underexplored problem is how to leverage the advantage of unlabeled data in…

Computer Vision and Pattern Recognition · Computer Science 2022-08-31 Junxiang Huang , Alexander Huang , Beatriz C. Guerra , Yen-Yun Yu

We categorize meta-learning evaluation into two settings: $\textit{in-distribution}$ [ID], in which the train and test tasks are sampled $\textit{iid}$ from the same underlying task distribution, and $\textit{out-of-distribution}$ [OOD], in…

Machine Learning · Computer Science 2021-10-29 Amrith Setlur , Oscar Li , Virginia Smith

In semi-supervised semantic segmentation, existing studies have shown promising results in academic settings with controlled splits of benchmark datasets. However, the potential benefits of leveraging significantly larger sets of unlabeled…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Wooseok Shin , Jisu Kang , Hyeonki Jeong , Jin Sob Kim , Sung Won Han

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment…

Machine Learning · Computer Science 2025-01-15 Yan Fan , Yu Wang , Pengfei Zhu , Qinghua Hu

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Zhijun Mai , Guosheng Hu , Dexiong Chen , Fumin Shen , Heng Tao Shen

We propose a dense image prediction out-of-distribution detection algorithm, called PixOOD, which does not require training on samples of anomalous data and is not designed for a specific application which avoids traditional training…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Tomáš Vojíř , Jan Šochman , Jiří Matas

3D semantic segmentation (3DSS) is an essential process in the creation of a safe autonomous driving system. However, deep learning models for 3D semantic segmentation often suffer from the class imbalance problem and out-of-distribution…

Computer Vision and Pattern Recognition · Computer Science 2022-03-02 Yancheng Pan , Fan Xie , Huijing Zhao