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++ ... A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. Aug 4, 2020 · The goal of Out-of-Distribution (OOD) generalization problem is to train a predictor that generalizes on all environments. Popular approaches in this field use the hypothesis that such a predictor shall be an \\textit{invariant predictor} that captures the mechanism that remains constant across environments. While these approaches have been experimentally successful in various case studies ... Mar 25, 2022 · All solutions mentioned above, such as regularization, multimodality, scaling, and invariant risk minimization, can improve distribution shift and out-of-distribution generalization, ultimately ... 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++ ... 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 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 ... 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 Aug 4, 2020 · The goal of Out-of-Distribution (OOD) generalization problem is to train a predictor that generalizes on all environments. Popular approaches in this field use the hypothesis that such a predictor shall be an \\textit{invariant predictor} that captures the mechanism that remains constant across environments. While these approaches have been experimentally successful in various case studies ... 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 ... 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 ... 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 ... high-risk applications [5,6]. To solve the problem, out-of-distribution (OOD) detection aims to distinguish and reject test samples with either covariate shifts or semantic shifts or both, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions [4]. Existing OOD detection methods mostly focus on cal- 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 ... 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. 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 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. Apr 19, 2023 · Recently, a class of compact and brain-inspired continuous-time recurrent neural networks has shown great promise in modeling autonomous navigation of ground ( 18, 19) and simulated drone vehicles end to end in a closed loop with their environments ( 21 ). These networks are called liquid time-constant (LTC) networks ( 35 ), or liquid networks. Feb 19, 2023 · Abstract. Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue. However, most existing algorithms for OOD generalization are complicated and ... Out-of-distribution (OOD) generalization algorithm [Shen et al., 2021; Wang et al., 2021b] aims to achieve satisfac-tory generalization performance under unknown distribution shifts. It has been occupying an important position in the re-search community due to the increasing demand for handling in-the-wild unseen data. Combining the strength of ... 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 ... 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 ... Sep 15, 2022 · The unique contribution of this paper is two-fold, justified by extensive experiments. First, we present a realistic problem setting of OOD task for skin lesion. Second, we propose an approach to target the long-tailed and fine-grained aspects of the problem setting simultaneously to increase the OOD performance. 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 Mar 3, 2021 · Then, we focus on a certain class of out of distribution problems, their assumptions, and introduce simple algorithms that follow from these assumptions that are able to provide more reliable generalization. A central topic in the thesis is the strong link between discovering the causal structure of the data, finding features that are reliable ... 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- 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. 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 ... 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. 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. Feb 19, 2023 · Abstract. Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue. However, most existing algorithms for OOD generalization are complicated and ... ODIN: Out-of-Distribution Detector for Neural Networks Feb 21, 2022 · Most existing datasets with category and viewpoint labels 13,26,27,28 present two major challenges: (1) lack of control over the distribution of categories and viewpoints, or (2) small size. Thus ... 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 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 ... 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. 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 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- 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 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). 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 ... 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. Evaluation under Distribution Shifts. Measure, Explore, and Exploit Data Heterogeneity. Distributionally Robust Optimization. Applications of OOD Generalization & Heterogeneity. I am looking for undergraduates to collaborate with. If you are interested in performance evaluation, robust learning, out-of-distribution generalization, etc. ODIN: Out-of-Distribution Detector for 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 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 ... ODIN: Out-of-Distribution Detector for Neural Networks 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. 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 examples of 2 in-distribution (from CIFAR-100) and 1 out-of-distribution class (from CIFAR-10). The color coding shows the Mahalanobis outlier score, while the points are projections of embeddings of members of the in-distribution CIFAR-100 classes "sunflowers" (black plus signs) and "turtle" Evaluation under Distribution Shifts. Measure, Explore, and Exploit Data Heterogeneity. Distributionally Robust Optimization. Applications of OOD Generalization & Heterogeneity. I am looking for undergraduates to collaborate with. If you are interested in performance evaluation, robust learning, out-of-distribution generalization, etc. 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 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 ... Evaluation under Distribution Shifts. Measure, Explore, and Exploit Data Heterogeneity. Distributionally Robust Optimization. Applications of OOD Generalization & Heterogeneity. I am looking for undergraduates to collaborate with. If you are interested in performance evaluation, robust learning, out-of-distribution generalization, etc. Out-of-distribution (OOD) generalization algorithm [Shen et al., 2021; Wang et al., 2021b] aims to achieve satisfac-tory generalization performance under unknown distribution shifts. It has been occupying an important position in the re-search community due to the increasing demand for handling in-the-wild unseen data. Combining the strength of ... 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. 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. CVF Open Access 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. Evaluation under Distribution Shifts. Measure, Explore, and Exploit Data Heterogeneity. Distributionally Robust Optimization. Applications of OOD Generalization & Heterogeneity. I am looking for undergraduates to collaborate with. If you are interested in performance evaluation, robust learning, out-of-distribution generalization, etc. examples of 2 in-distribution (from CIFAR-100) and 1 out-of-distribution class (from CIFAR-10). The color coding shows the Mahalanobis outlier score, while the points are projections of embeddings of members of the in-distribution CIFAR-100 classes "sunflowers" (black plus signs) and "turtle" Jan 22, 2019 · Out-of-distribution detection using an ensemble of self supervised leave-out classifiers A. Vyas, N. Jammalamadaka, X. Zhu, D. Das, B. Kaul, and T. L. Willke, “Out-of-distribution detection using an ensemble of self supervised leave-out classifiers,” in European Conference on Computer Vision, 2018, pp. 560–574. 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. 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. 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- 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- Sep 3, 2023 · Abstract. We study the out-of-distribution generalization of active learning that adaptively selects samples for annotation in learning the decision boundary of classification. Our empirical study finds that increasingly annotating seen samples may hardly benefit the generalization. To address the problem, we propose Counterfactual Active ... 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 ... 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 Sep 3, 2023 · Abstract. We study the out-of-distribution generalization of active learning that adaptively selects samples for annotation in learning the decision boundary of classification. Our empirical study finds that increasingly annotating seen samples may hardly benefit the generalization. To address the problem, we propose Counterfactual Active ... Aug 4, 2020 · The goal of Out-of-Distribution (OOD) generalization problem is to train a predictor that generalizes on all environments. Popular approaches in this field use the hypothesis that such a predictor shall be an \\textit{invariant predictor} that captures the mechanism that remains constant across environments. While these approaches have been experimentally successful in various case studies ... Aug 29, 2023 · ODIN is a preprocessing method for inputs that aims to increase the discriminability of the softmax outputs for In- and Out-of-Distribution data. Implements the Mahalanobis Method. Implements the Energy Score of Energy-based Out-of-distribution Detection. Uses entropy to detect OOD inputs. Implements the MaxLogit method. 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. 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 ... Apr 19, 2023 · Recently, a class of compact and brain-inspired continuous-time recurrent neural networks has shown great promise in modeling autonomous navigation of ground ( 18, 19) and simulated drone vehicles end to end in a closed loop with their environments ( 21 ). These networks are called liquid time-constant (LTC) networks ( 35 ), or liquid networks. Aug 4, 2020 · The goal of Out-of-Distribution (OOD) generalization problem is to train a predictor that generalizes on all environments. Popular approaches in this field use the hypothesis that such a predictor shall be an \\textit{invariant predictor} that captures the mechanism that remains constant across environments. While these approaches have been experimentally successful in various case studies ... 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++ ... 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.
Feb 19, 2023 · Abstract. Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue. However, most existing algorithms for OOD generalization are complicated and ... . Who is jiraiya
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). 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. 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 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 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 19, 2023 · Abstract. Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue. However, most existing algorithms for OOD generalization are complicated 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++ ... 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 19, 2023 · Recently, a class of compact and brain-inspired continuous-time recurrent neural networks has shown great promise in modeling autonomous navigation of ground ( 18, 19) and simulated drone vehicles end to end in a closed loop with their environments ( 21 ). These networks are called liquid time-constant (LTC) networks ( 35 ), or liquid networks. 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. 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 ... Evaluation under Distribution Shifts. Measure, Explore, and Exploit Data Heterogeneity. Distributionally Robust Optimization. Applications of OOD Generalization & Heterogeneity. I am looking for undergraduates to collaborate with. If you are interested in performance evaluation, robust learning, out-of-distribution generalization, etc. 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 ... 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. Evaluation under Distribution Shifts. Measure, Explore, and Exploit Data Heterogeneity. Distributionally Robust Optimization. Applications of OOD Generalization & Heterogeneity. I am looking for undergraduates to collaborate with. If you are interested in performance evaluation, robust learning, out-of-distribution generalization, etc. .