中文
相关论文

相关论文: Compressing Model with Few Class-Imbalance Samples…

200 篇论文

Recent research underscores the pivotal role of the Out-of-Distribution (OOD) feature representation field scale in determining the efficacy of models in OOD detection. Consequently, the adoption of model ensembles has emerged as a…

机器学习 · 计算机科学 2024-08-19 Chenhui Xu , Fuxun Yu , Zirui Xu , Nathan Inkawhich , Xiang Chen

Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions. In real-world scenarios, however, the efficacy of existing OOD detection methods is often impeded by…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Kai Liu , Zhihang Fu , Sheng Jin , Chao Chen , Ze Chen , Rongxin Jiang , Fan Zhou , Yaowu Chen , Jieping Ye

Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown…

机器学习 · 计算机科学 2026-05-28 Fengqiang Wan , Qing-Yuan Jiang , Yang Yang

Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored. Such few-shot OOD settings are challenging, as models have scarce…

机器学习 · 计算机科学 2023-12-27 Nikhil Mehta , Kevin J Liang , Jing Huang , Fu-Jen Chu , Li Yin , Tal Hassner

Few-shot Out-of-Distribution (OOD) detection has emerged as a critical research direction in machine learning for practical deployment. Most existing Few-shot OOD detection methods suffer from insufficient generalization capability for the…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Pinxuan Li , Bing Cao , Changqing Zhang , Qinghua Hu

Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance. Recent studies found that directly training with out-of-distribution data (i.e., open-set samples) in a semi-supervised manner would…

机器学习 · 计算机科学 2022-07-06 Hongxin Wei , Lue Tao , Renchunzi Xie , Lei Feng , Bo An

Although few-shot learning and one-class classification (OCC), i.e., learning a binary classifier with data from only one class, have been separately well studied, their intersection remains rather unexplored. Our work addresses the…

机器学习 · 计算机科学 2021-02-12 Ahmed Frikha , Denis Krompaß , Hans-Georg Köpken , Volker Tresp

Machine learning models often encounter samples that are diverged from the training distribution. Failure to recognize an out-of-distribution (OOD) sample, and consequently assign that sample to an in-class label significantly compromises…

计算机视觉与模式识别 · 计算机科学 2022-12-06 Mohammadreza Salehi , Hossein Mirzaei , Dan Hendrycks , Yixuan Li , Mohammad Hossein Rohban , Mohammad Sabokrou

Nowadays, classification and Out-of-Distribution (OoD) detection in the few-shot setting remain challenging aims due to rarity and the limited samples in the few-shot setting, and because of adversarial attacks. Accomplishing these aims is…

机器学习 · 计算机科学 2022-02-03 Nikolaos Dionelis , Mehrdad Yaghoobi , Sotirios A. Tsaftaris

Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learning models in the real world. Distance-based OOD detection…

机器学习 · 计算机科学 2024-02-06 Haodong Lu , Dong Gong , Shuo Wang , Jason Xue , Lina Yao , Kristen Moore

Generative models trained in an unsupervised manner may set high likelihood and low reconstruction loss to Out-of-Distribution (OoD) samples. This increases Type II errors and leads to missed anomalies, overall decreasing Anomaly Detection…

机器学习 · 计算机科学 2022-02-03 Nikolaos Dionelis , Mehrdad Yaghoobi , Sotirios A. Tsaftaris

Distributionally robust optimization (DRO) and invariant risk minimization (IRM) are two popular methods proposed to improve out-of-distribution (OOD) generalization performance of machine learning models. While effective for small models,…

机器学习 · 计算机科学 2023-01-25 Xiao Zhou , Yong Lin , Renjie Pi , Weizhong Zhang , Renzhe Xu , Peng Cui , Tong Zhang

In this work, we propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. Specifically, we exploit the easily available out-of-distribution samples to drive…

机器学习 · 计算机科学 2022-06-13 Duong H. Le , Khoi D. Nguyen , Khoi Nguyen , Quoc-Huy Tran , Rang Nguyen , Binh-Son Hua

The reliability of artificial intelligence (AI) systems in open-world settings depends heavily on their ability to flag out-of-distribution (OOD) inputs unseen during training. Recent advances in large-scale vision-language models (VLMs)…

机器学习 · 计算机科学 2025-10-14 Faizul Rakib Sayem , Shahana Ibrahim

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…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Mingle Xu , Jaehwan Lee , Sook Yoon , Dong Sun Park

Out-of-distribution (OOD) detection attempts to distinguish outlier samples to prevent models trained on the in-distribution (ID) dataset from producing unavailable outputs. Most OOD detection methods require many IID samples for training,…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Xiang Fang , Arvind Easwaran , Blaise Genest

The deployment of machine learning solutions in real-world scenarios often involves addressing the challenge of out-of-distribution (OOD) detection. While significant efforts have been devoted to OOD detection in classical supervised…

计算机视觉与模式识别 · 计算机科学 2023-11-10 Loïc Le Bescond , Maria Vakalopoulou , Stergios Christodoulidis , Fabrice André , Hugues Talbot

Detecting out-of-distribution (OOD) samples is essential for neural networks operating in open-world settings, particularly in safety-critical applications. Existing methods have improved OOD detection by leveraging two main techniques:…

计算机视觉与模式识别 · 计算机科学 2025-09-01 Lucas Rakotoarivony

Numerous machine learning (ML) models have been developed, including those for software engineering (SE) tasks, under the assumption that training and testing data come from the same distribution. However, training and testing distributions…

软件工程 · 计算机科学 2025-03-04 Yanfu Yan , Viet Duong , Huajie Shao , Denys Poshyvanyk

Foundational models, trained on vast and diverse datasets, have demonstrated remarkable capabilities in generalizing across different domains and distributions for various zero-shot tasks. Our work addresses the challenge of retaining these…

计算机视觉与模式识别 · 计算机科学 2024-09-13 Tom Shaked , Yuval Goldman , Oran Shayer
‹ 上一页 1 2 3 10 下一页 ›