633 citations · 2.7k across the 61 of their papers we have counts for
35 papers · 1 filter
Dream the Impossible: Outlier Imagination with Diffusion Models
Xuefeng Du, Yiyou Sun, Xiaojin Zhu +1
Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor…
When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
Yiyou Sun, Zhenmei Shi, Yingyu Liang +1
Novel Class Discovery (NCD) aims at inferring novel classes in an unlabeled set by leveraging prior knowledge from a labeled set with known classes. Despite its importance, there i…
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Jingyang Zhang, Jingkang Yang, Pengyun Wang +9
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods…
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Haoyue Bai, Gregory Canal, Xuefeng Du +3
Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OO…
Distributionally Robust Optimization with Probabilistic Group
Soumya Suvra Ghosal, Yixuan Li
Modern machine learning models may be susceptible to learning spurious correlations that hold on average but not for the atypical group of samples. To address the problem, previous…
Non-Parametric Outlier Synthesis
Leitian Tao, Xuefeng Du, Xiaojin Zhu +1
Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. One of the key challenges is that models lack supervision signals fro…
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
Hongxin Wei, Huiping Zhuang, Renchunzi Xie +4
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been s…
Is Out-of-Distribution Detection Learnable?
Zhen Fang, Yixuan Li, Jie Lu +3
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studi…
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Haobo Wang, Mingxuan Xia, Yixuan Li +4
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single grou…
Out-of-distribution Detection via Frequency-regularized Generative Models
Mu Cai, Yixuan Li
Modern deep generative models can assign high likelihood to inputs drawn from outside the training distribution, posing threats to models in open-world deployments. While much rese…
OpenCon: Open-world Contrastive Learning
Yiyou Sun, Yixuan Li
Machine learning models deployed in the wild naturally encounter unlabeled samples from both known and novel classes. Challenges arise in learning from both the labeled and unlabel…
Task Agnostic and Post-hoc Unseen Distribution Detection
Radhika Dua, Seongjun Yang, Yixuan Li +1
Despite the recent advances in out-of-distribution(OOD) detection, anomaly detection, and uncertainty estimation tasks, there do not exist a task-agnostic and post-hoc approach. To…
POEM: Out-of-Distribution Detection with Posterior Sampling
Yifei Ming, Ying Fan, Yixuan Li
Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also…
Mitigating Neural Network Overconfidence with Logit Normalization
Hongxin Wei, Renchunzi Xie, Hao Cheng +3
Detecting out-of-distribution inputs is critical for safe deployment of machine learning models in the real world. However, neural networks are known to suffer from the overconfide…
Out-of-Distribution Detection with Deep Nearest Neighbors
Yiyou Sun, Yifei Ming, Xiaojin Zhu +1
Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world. Distance-based methods have demonstrated promise, where testing samp…
Training OOD Detectors in their Natural Habitats
Julian Katz-Samuels, Julia Nakhleh, Robert Nowak +1
Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OO…
VOS: Learning What You Don't Know by Virtual Outlier Synthesis
Xuefeng Du, Zhaoning Wang, Mu Cai +1
Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lac…
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Haobo Wang, Ruixuan Xiao, Yixuan Li +4
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation s…
ReAct: Out-of-distribution Detection With Rectified Activations
Yiyou Sun, Chuan Guo, Yixuan Li
Out-of-distribution (OOD) detection has received much attention lately due to its practical importance in enhancing the safe deployment of neural networks. One of the primary chall…
DICE: Leveraging Sparsification for Out-of-Distribution Detection
Yiyou Sun, Yixuan Li
Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world. Previous methods commonly rely on an OOD score der…
Can multi-label classification networks know what they don't know?
Haoran Wang, Weitang Liu, Alex Bocchieri +1
Estimating out-of-distribution (OOD) uncertainty is a central challenge for safely deploying machine learning models in the open-world environment. Improved methods for OOD detecti…
Natural Attribute-based Shift Detection
Jeonghoon Park, Jimin Hong, Radhika Dua +4
Despite the impressive performance of deep networks in vision, language, and healthcare, unpredictable behaviors on samples from the distribution different than the training distri…
On the Importance of Gradients for Detecting Distributional Shifts in the Wild
Rui Huang, Andrew Geng, Yixuan Li
Detecting out-of-distribution (OOD) data has become a critical component in ensuring the safe deployment of machine learning models in the real world. Existing OOD detection approa…
On the Impact of Spurious Correlation for Out-of-distribution Detection
Yifei Ming, Hang Yin, Yixuan Li
Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research at…