中文
相关论文

相关论文: VOS: Learning What You Don't Know by Virtual Outli…

200 篇论文

Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection that…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Ji Zhang , Lianli Gao , Bingguang Hao , Hao Huang , Jingkuan Song , Hengtao Shen

Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of machine learning systems in the real world. Great progress has been made over the past years. This paper presents the first review of recent advances…

计算与语言 · 计算机科学 2023-12-29 Hao Lang , Yinhe Zheng , Yixuan Li , Jian Sun , Fei Huang , Yongbin Li

Accurate trajectory prediction is essential for the safe operation of autonomous vehicles in real-world environments. Even well-trained machine learning models may produce unreliable predictions due to discrepancies between training data…

机器人学 · 计算机科学 2025-04-24 Tongfe Guo , Taposh Banerjee , Rui Liu , Lili Su

Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversity of the OOD examples makes such methods fragile. There are…

计算机视觉与模式识别 · 计算机科学 2022-03-22 Haoqi Wang , Zhizhong Li , Litong Feng , Wayne Zhang

Out-of-distribution (OOD) detection, crucial for reliable pattern classification, discerns whether a sample originates outside the training distribution. This paper concentrates on the high-dimensional features output by the final…

计算机视觉与模式识别 · 计算机科学 2024-05-06 Qiuyu Zhu , Yiwei He

Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications. Existing methods typically focus on feature representations or output-space analysis, often assuming a…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Mostafa ElAraby , Sabyasachi Sahoo , Yann Pequignot , Paul Novello , Liam Paull

It is an important problem in trustworthy machine learning to recognize out-of-distribution (OOD) inputs which are inputs unrelated to the in-distribution task. Many out-of-distribution detection methods have been suggested in recent years.…

机器学习 · 计算机科学 2022-06-22 Julian Bitterwolf , Alexander Meinke , Maximilian Augustin , Matthias Hein

As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms.…

机器学习 · 计算机科学 2018-09-12 Apoorv Vyas , Nataraj Jammalamadaka , Xia Zhu , Dipankar Das , Bharat Kaul , Theodore L. Willke

State-of-the-art Object Detection (OD) methods predominantly operate under a closed-world assumption, where test-time categories match those encountered during training. However, detecting and localizing unknown objects is crucial for…

计算机视觉与模式识别 · 计算机科学 2025-06-18 Daniel Montoya , Aymen Bouguerra , Alexandra Gomez-Villa , Fabio Arnez

Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the…

机器学习 · 计算机科学 2023-11-07 Reza Averly , Wei-Lun Chao

Out-of-distribution (OOD) detection aims to detect test samples outside the training category space, which is an essential component in building reliable machine learning systems. Existing reviews on OOD detection primarily focus on method…

机器学习 · 计算机科学 2025-08-05 Shuo Lu , Yingsheng Wang , Lijun Sheng , Lingxiao He , Aihua Zheng , Jian Liang

Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task. However, the performance of panoptic segmentation is severely impacted in the presence of…

计算机视觉与模式识别 · 计算机科学 2023-10-19 Rohit Mohan , Kiran Kumaraswamy , Juana Valeria Hurtado , Kürsat Petek , Abhinav Valada

It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task…

A key feature of out-of-distribution (OOD) detection is to exploit a trained neural network by extracting statistical patterns and relationships through the multi-layer classifier to detect shifts in the expected input data distribution.…

机器学习 · 计算机科学 2023-06-07 Eduardo Dadalto , Pierre Colombo , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recent studies in OOD detection utilize the information from…

计算与语言 · 计算机科学 2022-10-21 Hyunsoo Cho , Choonghyun Park , Jaewook Kang , Kang Min Yoo , Taeuk Kim , Sang-goo Lee

Out-of-Distribution (OOD) detection, i.e., identifying whether an input is sampled from a novel distribution other than the training distribution, is a critical task for safely deploying machine learning systems in the open world. Recently,…

机器学习 · 计算机科学 2023-01-13 Feng Xue , Zi He , Chuanlong Xie , Falong Tan , Zhenguo Li

Out-of-distribution (OoD) detection is a natural downstream task for deep generative models, due to their ability to learn the input probability distribution. There are mainly two classes of approaches for OoD detection using deep…

机器学习 · 计算机科学 2019-07-11 Yujia Huang , Sihui Dai , Tan Nguyen , Richard G. Baraniuk , Anima Anandkumar

This paper presents a novel evaluation framework for Out-of-Distribution (OOD) detection that aims to assess the performance of machine learning models in more realistic settings. We observed that the real-world requirements for testing OOD…

计算机视觉与模式识别 · 计算机科学 2023-09-01 Vahid Reza Khazaie , Anthony Wong , Mohammad Sabokrou

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,…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Chaohua Li , Enhao Zhang , Chuanxing Geng , Songcan Chen

Deep neural networks are increasingly used in a wide range of technologies and services, but remain highly susceptible to out-of-distribution (OOD) samples, that is, drawn from a different distribution than the original training set. A…

机器学习 · 计算机科学 2024-04-17 Pietro Recalcati , Fabio Garcea , Luca Piano , Fabrizio Lamberti , Lia Morra