Jun 1, 2022 · In part I, we considered the case where we have a clean set of unlabelled data and must determine if a new sample comes from the same set. In part II, we considered the open-set recognition scenario where we also have class labels. This is particularly relevant to the real-world deployment of classifiers, which will inevitably encounter OOD data. Feb 16, 2022 · To solve this critical problem, out-of-distribution (OOD) generalization on graphs, which goes beyond the I.I.D. hypothesis, has made great progress and attracted ever-increasing attention from the research community. In this paper, we comprehensively survey OOD generalization on graphs and present a detailed review of recent advances in this area. Hendrycks & Gimpel proposed a baseline method to detect out-of-distribution examples without further re-training networks. The method is based on an observation that a well-trained neural network tends to assign higher softmax scores to in-distribution examples than out-of-distribution Work done while at Cornell University. 1 Let Dout denote an out-of-distribution dataset of (xout;y out)pairs where yout 2Y := fK+1;:::;K+Og;Yout\Yin =;. Depending on how different Dout is from Din, we categorize the OOD detection tasks into near-OOD and far-OOD. We first study the scenario where the model is fine-tuned only on the training set D in train without any access to OOD ... out-of-distribution. We present a simple baseline that utilizes probabilities from softmax distributions. Correctly classified examples tend to have greater maxi-mum softmax probabilities than erroneously classified and out-of-distribution ex-amples, allowing for their detection. We assess performance by defining sev- However, using GANs to detect out-of-distribution instances by measuring the likelihood under the data distribution can fail (Nalisnick et al.,2019), while VAEs often generate ambiguous and blurry explanations. More recently, some re-searchers have argued that using auxiliary generative models in counterfactual generation incurs an engineering ... ODIN: Out-of-Distribution Detector for Neural Networks Sep 15, 2022 · Out-of-Distribution Representation Learning for Time Series Classification. Wang Lu, Jindong Wang, Xinwei Sun, Yiqiang Chen, Xing Xie. Time series classification is an important problem in real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen ... A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data. machine-learning deep-learning pytorch ... Aug 24, 2022 · We include results for four types of out-of-distribution samples: (1) dataset shift, where we evaluate the model on two other datasets with differences in the acquisition and population patterns (2) transformation shift where we apply artificial transformations to our ID data, (3) diagnostic shift, where we compare Covid-19 to non-Covid ... Feb 16, 2022 · Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where ... Feb 16, 2022 · To solve this critical problem, out-of-distribution (OOD) generalization on graphs, which goes beyond the I.I.D. hypothesis, has made great progress and attracted ever-increasing attention from the research community. In this paper, we comprehensively survey OOD generalization on graphs and present a detailed review of recent advances in this area. Towards Out-Of-Distribution Generalization: A Survey Jiashuo Liu*, Zheyan Shen∗, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, Peng Cui† Department of Computer Science and Technology Tsinghua University [email protected], [email protected], [email protected] Abstract ... Nov 26, 2021 · Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increase in attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most ... Oct 28, 2022 · Out-of-Distribution (OOD) detection separates ID (In-Distribution) data and OOD data from input data through a model. This problem has attracted increasing attention in the area of machine learning. OOD detection has achieved good intrusion detection, fraud detection, system health monitoring, sensor network event detection, and ecosystem interference detection. The method based on deep ... marginal distribution of P X,Y for the input variable Xby P 0.Given a test input x ∈X, the problem of out-of-distribution detection can be formulated as a single-sample hypothesis testing task: H 0: x ∼P 0, vs. H 1: x ≁P 0. (1) Here the null hypothesis H 0 implies that the test input x is an in-distribution sample. The goal of Hendrycks & Gimpel proposed a baseline method to detect out-of-distribution examples without further re-training networks. The method is based on an observation that a well-trained neural network tends to assign higher softmax scores to in-distribution examples than out-of-distribution Work done while at Cornell University. 1 While out-of-distribution (OOD) generalization, robustness, and detection have been discussed in works related to reducing existential risks from AI (e.g., [Amodei et al., 2016, Hendrycks et al., 2022b]) the truth is that the vast majority of distribution shifts are not directly related to existential risks. Dec 17, 2020 · While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, where the test data come from another distribution (w.r.t. the training one). Designing a general OoD generalization framework to a wide range of applications is challenging, mainly due to possible correlation shift ... Aug 31, 2021 · This paper represents the first comprehensive, systematic review of OOD generalization, encompassing a spectrum of aspects from problem definition, methodological development, and evaluation procedures, to the implications and future directions of the field. Aug 24, 2022 · We include results for four types of out-of-distribution samples: (1) dataset shift, where we evaluate the model on two other datasets with differences in the acquisition and population patterns (2) transformation shift where we apply artificial transformations to our ID data, (3) diagnostic shift, where we compare Covid-19 to non-Covid ... Apr 16, 2021 · Deep Stable Learning for Out-Of-Distribution Generalization. Xingxuan Zhang, Peng Cui, Renzhe Xu, Linjun Zhou, Yue He, Zheyan Shen. Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of ... Hendrycks & Gimpel proposed a baseline method to detect out-of-distribution examples without further re-training networks. The method is based on an observation that a well-trained neural network tends to assign higher softmax scores to in-distribution examples than out-of-distribution Work done while at Cornell University. 1 Apr 16, 2021 · Deep Stable Learning for Out-Of-Distribution Generalization. Xingxuan Zhang, Peng Cui, Renzhe Xu, Linjun Zhou, Yue He, Zheyan Shen. Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of ... Dec 17, 2019 · The likelihood is dominated by the “background” pixels, whereas the likelihood ratio focuses on the “semantic” pixels and is thus better for OOD detection. Our likelihood ratio method corrects the background effect and significantly improves the OOD detection of MNIST images from an AUROC score of 0.089 to 0.994, based on a PixelCNN++ ... Sep 15, 2022 · Out-of-Distribution Representation Learning for Time Series Classification. Wang Lu, Jindong Wang, Xinwei Sun, Yiqiang Chen, Xing Xie. Time series classification is an important problem in real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen ... Nov 26, 2021 · Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increase in attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most ... May 15, 2022 · 1. We propose an unsupervised method to distinguish in-distribution from out-of-distribution input. The results indicate that the assumptions and methods of outlier and deep anomaly detection are also relevant to the field of out-of-distribution detection. 2. The method works on the basis of an Isolation Forest. Hendrycks & Gimpel proposed a baseline method to detect out-of-distribution examples without further re-training networks. The method is based on an observation that a well-trained neural network tends to assign higher softmax scores to in-distribution examples than out-of-distribution Work done while at Cornell University. 1 cause of model crash under distribution shifts, they propose to realize out-of-distribution generalization by decorrelat-ing the relevant and irrelevant features. Since there is no extra supervision for separating relevant features from ir-relevant features, a conservative solution is to decorrelate all features. Jun 6, 2021 · Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision ... We evaluate our method on a diverse set of in- and out-of-distribution dataset pairs. In many settings, our method outperforms other methods by a large margin. The contri-butions of our paper are summarized as follows: • We propose a novel experimental setting and a novel training methodology for out-of-distribution detection in neural networks. We have summarized the main branches of works for Out-of-Distribution(OOD) Generalization problem, which are classified according to the research focus, including unsupervised representation learning, supervised learning models and optimization methods. For more details, please refer to our survey on OOD generalization. Sep 15, 2022 · Out-of-Distribution Representation Learning for Time Series Classification. Wang Lu, Jindong Wang, Xinwei Sun, Yiqiang Chen, Xing Xie. Time series classification is an important problem in real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen ... novelty detection (ND), open set recognition (OSR), out-of-distribution (OOD) detection, and outlier detection (OD). These sub-topics can be similar in the sense that they all define a certain in-distribution, with the common goal of detecting out-of-distribution samples under the open-world assumption. However, subtle differences exist among ... Jul 1, 2021 · In the classification problem, out-of-distribution data means data with classes not included in the training data. Detecting such out-of-distribution data is a critical problem in the stability of an image classification model using deep learning [10 ]. We define wafer map data with a form other than the 16 types of wafer maps corresponding to ... To clarify the distinction between in-stock distribution, out-of-stock (OOS) distribution, and loss of distribution, it is essential to understand the dynamics of product availability and stock levels. Let’s refer to Exhibit 29.14, which provides an example of a brand’s incidence of purchase and stocks across four time periods. Aug 31, 2021 · This paper represents the first comprehensive, systematic review of OOD generalization, encompassing a spectrum of aspects from problem definition, methodological development, and evaluation procedures, to the implications and future directions of the field. Nov 26, 2021 · Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increase in attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most ... Jan 25, 2021 · The term 'out-of-distribution' (OOD) data refers to data that was collected at a different time, and possibly under different conditions or in a different environment, then the data collected to create the model. They may say that this data is from a 'different distribution'. Data that is in-distribution can be called novelty data. May 15, 2022 · 1. We propose an unsupervised method to distinguish in-distribution from out-of-distribution input. The results indicate that the assumptions and methods of outlier and deep anomaly detection are also relevant to the field of out-of-distribution detection. 2. The method works on the basis of an Isolation Forest. Out-of-distribution Neural networks and out-of-distribution data. A crucial criterion for deploying a strong classifier in many real-world... Out-of-Distribution (ODD). For Language and Vision activities, the term “distribution” has slightly different meanings. Various ODD detection techniques. This ... We evaluate our method on a diverse set of in- and out-of-distribution dataset pairs. In many settings, our method outperforms other methods by a large margin. The contri-butions of our paper are summarized as follows: • We propose a novel experimental setting and a novel training methodology for out-of-distribution detection in neural networks. Mar 21, 2022 · 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 OOD samples that are easy to identify in the feature space while hard to distinguish in the logit space and vice versa. Motivated by this observation, we ... May 15, 2022 · 1. We propose an unsupervised method to distinguish in-distribution from out-of-distribution input. The results indicate that the assumptions and methods of outlier and deep anomaly detection are also relevant to the field of out-of-distribution detection. 2. The method works on the basis of an Isolation Forest. However, using GANs to detect out-of-distribution instances by measuring the likelihood under the data distribution can fail (Nalisnick et al.,2019), while VAEs often generate ambiguous and blurry explanations. More recently, some re-searchers have argued that using auxiliary generative models in counterfactual generation incurs an engineering ... While out-of-distribution (OOD) generalization, robustness, and detection have been discussed in works related to reducing existential risks from AI (e.g., [Amodei et al., 2016, Hendrycks et al., 2022b]) the truth is that the vast majority of distribution shifts are not directly related to existential risks. Oct 21, 2021 · Abstract: Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving system to issue an alert and hand over the control to humans when it detects unusual scenes or objects that it has never seen during training time and cannot ... Dec 17, 2020 · While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, where the test data come from another distribution (w.r.t. the training one). Designing a general OoD generalization framework to a wide range of applications is challenging, mainly due to possible correlation shift ... Feb 1, 2023 · TL;DR: We propose a novel out-of-distribution detection method motivated by Modern Hopfield Energy, and futhur derive a simplified version that is effective, efficient and hyperparameter-free. Abstract : Out-of-Distribution (OOD) detection is essential for safety-critical applications of deep neural networks. Feb 16, 2022 · Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where ... To clarify the distinction between in-stock distribution, out-of-stock (OOS) distribution, and loss of distribution, it is essential to understand the dynamics of product availability and stock levels. Let’s refer to Exhibit 29.14, which provides an example of a brand’s incidence of purchase and stocks across four time periods. Nov 26, 2021 · Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increase in attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most ... Out-of-Distribution (OOD) Detection with Deep Neural Networks based on PyTorch. and is designed such that it should be compatible with frameworks like pytorch-lightning and pytorch-segmentation-models . The library also covers some methods from closely related fields such as Open-Set Recognition, Novelty Detection, Confidence Estimation and ... marginal distribution of P X,Y for the input variable Xby P 0.Given a test input x ∈X, the problem of out-of-distribution detection can be formulated as a single-sample hypothesis testing task: H 0: x ∼P 0, vs. H 1: x ≁P 0. (1) Here the null hypothesis H 0 implies that the test input x is an in-distribution sample. The goal of Mar 2, 2020 · Out-of-Distribution Generalization via Risk Extrapolation (REx) Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but ... The outputs of an ensemble of networks can be used to estimate the uncertainty of a classifier. At test time, the estimated uncertainty for out-of-distribution samples turns out to be higher than the one for in-distribution samples. 3. level 2. AnvaMiba. Mar 2, 2020 · Out-of-Distribution Generalization via Risk Extrapolation (REx) Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but ... [ICML2022] Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities [ICML2022] Scaling Out-of-Distribution Detection for Real-World Settings [ICML2022] POEM: Out-of-Distribution Detection with Posterior Sampling [NeurIPS2022] Deep Ensembles Work, But Are They Necessary? this to be out-of-distribution clustering. Once a model Mhas been trained on the class homogeneity task, we can evaluate it for both out-of-distribution classification and out-of-distribution clustering. For the former, in which we are given x~ from a sample-label pair (~x;~y j~y = 2Y train), we can classify x~ by comparing it with samples of The outputs of an ensemble of networks can be used to estimate the uncertainty of a classifier. At test time, the estimated uncertainty for out-of-distribution samples turns out to be higher than the one for in-distribution samples. 3. level 2. AnvaMiba. Feb 1, 2023 · TL;DR: We propose a novel out-of-distribution detection method motivated by Modern Hopfield Energy, and futhur derive a simplified version that is effective, efficient and hyperparameter-free. Abstract : Out-of-Distribution (OOD) detection is essential for safety-critical applications of deep neural networks. Jun 6, 2021 · Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision ... Feb 21, 2022 · It is well known that fine-tuning leads to better accuracy in-distribution (ID). However, in this paper, we find that fine-tuning can achieve worse accuracy than linear probing out-of-distribution (OOD) when the pretrained features are good and the distribution shift is large. On 10 distribution shift datasets (Breeds-Living17, Breeds-Entity30 ... ing data distribution p(x;y). At inference time, given an input x02Xthe goal of OOD detection is to identify whether x0is a sample drawn from p(x;y). 2.2 Types of Distribution Shifts As in (Ren et al.,2019), we assume that any repre-sentation of the input x, ˚(x), can be decomposed into two independent and disjoint components: the background ... In-distribution Out-of-distribution Figure 1. Learned confidence estimates can be used to easily sep-arate in- and out-of-distribution examples. Here, the CIFAR-10 test set is used as the in-distribution dataset, and TinyImageNet, LSUN, and iSUN are used as the out-of-distribution datasets. The model is trained using a DenseNet architecture. The outputs of an ensemble of networks can be used to estimate the uncertainty of a classifier. At test time, the estimated uncertainty for out-of-distribution samples turns out to be higher than the one for in-distribution samples. 3. level 2. AnvaMiba. A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data. machine-learning deep-learning pytorch ... Jan 25, 2021 · The term 'out-of-distribution' (OOD) data refers to data that was collected at a different time, and possibly under different conditions or in a different environment, then the data collected to create the model. They may say that this data is from a 'different distribution'. Data that is in-distribution can be called novelty data. Let Dout denote an out-of-distribution dataset of (xout;y out)pairs where yout 2Y := fK+1;:::;K+Og;Yout\Yin =;. Depending on how different Dout is from Din, we categorize the OOD detection tasks into near-OOD and far-OOD. We first study the scenario where the model is fine-tuned only on the training set D in train without any access to OOD ... Oct 21, 2021 · Abstract: Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving system to issue an alert and hand over the control to humans when it detects unusual scenes or objects that it has never seen during training time and cannot ... Jul 1, 2021 · In the classification problem, out-of-distribution data means data with classes not included in the training data. Detecting such out-of-distribution data is a critical problem in the stability of an image classification model using deep learning [10 ]. We define wafer map data with a form other than the 16 types of wafer maps corresponding to ... trained in the closed-world setting, the out-of-distribution (OOD) issue arises and deteriorates customer experience when the models are deployed in production, facing inputs comingfromtheopenworld[9]. Forinstance,amodelmay wrongly but confidently classify an image of crab into the clappingclass,eventhoughnocrab-relatedconceptsappear in the ... Jul 1, 2021 · In general, out-of-distribution data refers to data having a distribution different from that of training data. In the classification problem, out-of-distribution means data with classes that are not included in the training data. In image classification using the deep neural network, the research has been actively conducted to improve the ... We evaluate our method on a diverse set of in- and out-of-distribution dataset pairs. In many settings, our method outperforms other methods by a large margin. The contri-butions of our paper are summarized as follows: • We propose a novel experimental setting and a novel training methodology for out-of-distribution detection in neural networks. trained in the closed-world setting, the out-of-distribution (OOD) issue arises and deteriorates customer experience when the models are deployed in production, facing inputs comingfromtheopenworld[9]. Forinstance,amodelmay wrongly but confidently classify an image of crab into the clappingclass,eventhoughnocrab-relatedconceptsappear in the ... Feb 16, 2022 · Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where ... Apr 16, 2021 · Deep Stable Learning for Out-Of-Distribution Generalization. Xingxuan Zhang, Peng Cui, Renzhe Xu, Linjun Zhou, Yue He, Zheyan Shen. Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of ...
We have summarized the main branches of works for Out-of-Distribution(OOD) Generalization problem, which are classified according to the research focus, including unsupervised representation learning, supervised learning models and optimization methods. For more details, please refer to our survey on OOD generalization. . What time do culver
Out-of-Distribution (OOD) Detection with Deep Neural Networks based on PyTorch. and is designed such that it should be compatible with frameworks like pytorch-lightning and pytorch-segmentation-models . The library also covers some methods from closely related fields such as Open-Set Recognition, Novelty Detection, Confidence Estimation and ... Dec 17, 2019 · The likelihood is dominated by the “background” pixels, whereas the likelihood ratio focuses on the “semantic” pixels and is thus better for OOD detection. Our likelihood ratio method corrects the background effect and significantly improves the OOD detection of MNIST images from an AUROC score of 0.089 to 0.994, based on a PixelCNN++ ... Dec 25, 2020 · Out-of-Distribution Detection in Deep Neural Networks Outline:. A bit on OOD. The term “distribution” has slightly different meanings for Language and Vision tasks. Consider a dog... Approaches to Detect OOD instances:. One class of OOD detection techniques is based on thresholding over the ... Dec 17, 2019 · The likelihood is dominated by the “background” pixels, whereas the likelihood ratio focuses on the “semantic” pixels and is thus better for OOD detection. Our likelihood ratio method corrects the background effect and significantly improves the OOD detection of MNIST images from an AUROC score of 0.089 to 0.994, based on a PixelCNN++ ... 1ODIN: Out-of-DIstribution detector for Neural networks [21] failures are therefore often silent in that they do not result in explicit errors in the model. The above issue had been formulated as a problem of detecting whether an input data is from in-distribution (i.e. the training distribution) or out-of-distribution (i.e. a distri- ODIN: Out-of-Distribution Detector for Neural Networks cannot deliver reliable reasoning results when facing out-of-distribution samples. Next, even if supervision signals can be properly propagated between the neural and symbolic models, it is still possible that the NN predicts spurious fea-tures, leading to bad generalization performance (an exam-ple is provided in Sec. 6). Feb 16, 2022 · Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where ... ing data distribution p(x;y). At inference time, given an input x02Xthe goal of OOD detection is to identify whether x0is a sample drawn from p(x;y). 2.2 Types of Distribution Shifts As in (Ren et al.,2019), we assume that any repre-sentation of the input x, ˚(x), can be decomposed into two independent and disjoint components: the background ... Nov 11, 2021 · We propose Velodrome, a semi-supervised method of out-of-distribution generalization that takes labelled and unlabelled data from different resources as input and makes generalizable predictions. out-of-distribution examples, assuming our training set only contains older defendants referred as in-dis-tribution examples. The fractions of data are only for illustrative purposes. See details of in-distribution vs. out-of-distribution setup in §3.2. assistance, human-AI teams should outperform AI alone and human alone (e.g., in accuracy; also Nov 11, 2021 · We propose Velodrome, a semi-supervised method of out-of-distribution generalization that takes labelled and unlabelled data from different resources as input and makes generalizable predictions. .