Related papers: D-GAP: Improving Out-of-Domain Robustness via Data…

Out-of-domain (OOD) robustness under domain adaptation settings, where labeled source data and unlabeled target data come from different distributions, is a key challenge in real-world applications. A common approach to improving OOD…

Models trained on one set of domains often suffer performance drops on unseen domains, e.g., when wildlife monitoring models are deployed in new camera locations. In this work, we study principles for designing data augmentations for…

Deep learning has been demonstrated with tremendous success in recent years. Despite so, its performance in practice often degenerates drastically when encountering out-of-distribution (OoD) data, i.e. training and test data are sampled…

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained…

Deep learning models can perform well when evaluated on images from the same distribution as the training set. However, applying small perturbations in the forms of noise, artifacts, occlusions, blurring, etc. to a model's input image and…

Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets for measuring a model's OOD performance were designed to be…

One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addressing this issue is known as Out-of-Distribution (OOD)…

Deep neural networks have shown remarkable performance in image classification. However, their performance significantly deteriorates with corrupted input data. Domain generalization methods have been proposed to train robust models against…

Graph Anomaly Detection (GAD) aims to identify nodes that deviate from the majority within a graph, playing a crucial role in applications such as social networks and e-commerce. Despite the current advancements in deep learning-based GAD,…

The fidelity of Generative Adversarial Networks (GAN) inversion is impeded by Out-Of-Domain (OOD) areas (e.g., background, accessories) in the image. Detecting the OOD areas beyond the generation ability of the pre-trained model and…

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…

Most existing deep learning models are trained based on the closed-world assumption, where the test data is assumed to be drawn i.i.d. from the same distribution as the training data, known as in-distribution (ID). However, when models are…

When testing data and training data come from different distributions, deep neural networks (DNNs) will face significant safety risks in practical applications. Therefore, out-of-distribution (OOD) detection techniques, which can identify…

To deal with distribution shifts in graph data, various graph out-of-distribution (OOD) generalization techniques have been recently proposed. These methods often employ a two-step strategy that first creates augmented environments and…

Deep neural networks (DNNs) have become the de facto learning mechanism in different domains. Their tendency to perform unreliably on out-of-distribution (OOD) inputs hinders their adoption in critical domains. Several approaches have been…

Deep neural networks (DNNs), while increasingly deployed in many applications, struggle with robustness against anomalous and out-of-distribution (OOD) data. Current OOD benchmarks often oversimplify, focusing on single-object tasks and not…

Building object detectors that are robust to domain shifts is critical for real-world applications. Prior approaches fine-tune a pre-trained backbone and risk overfitting it to in-distribution (ID) data and distorting features useful for…

Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. While adaptive gradient methods theory is well understood for minimization problems, the…

Out-of-distribution (OOD) generalization remains a central challenge in deploying deep learning models to real-world scenarios, particularly in domains such as biomedical images, where distribution shifts are both subtle and pervasive.…

Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain…