Related papers: CIFAR-10-Warehouse: Broad and More Realistic Testb…

Neural networks are promising tools for high-throughput and accurate transmission electron microscopy (TEM) analysis of nanomaterials, but are known to generalize poorly on data that is "out-of-distribution" from their training data. Given…

Modern AI models excel in controlled settings but often fail in real-world scenarios where data distributions shift unpredictably - a challenge known as domain generalisation (DG). This paper tackles this limitation by rigorously evaluating…

The quality of generative models depends on the quality of the data they are trained on. Creating large-scale, high-quality datasets is often expensive and sometimes impossible, e.g. in certain scientific applications where there is no…

Focus stacking is widely used in micro, macro, and landscape photography to reconstruct all-in-focus images from multiple frames obtained with focus bracketing, that is, with shallow depth of field and different focus planes. Existing deep…

Recent generative models produce images with a level of authenticity that makes them nearly indistinguishable from real photos and artwork. Potential harmful use cases of these models, necessitate the creation of robust synthetic image…

Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI. Closely packed objects cause inevitable occlusions, making safe action generation particularly difficult. Under such…

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…

We systematically study a wide variety of generative models spanning semantically-diverse image datasets to understand and improve the feature extractors and metrics used to evaluate them. Using best practices in psychophysics, we measure…

Detecting out-of-distribution examples is important for safety-critical machine learning applications such as detecting novel biological phenomena and self-driving cars. However, existing research mainly focuses on simple small-scale…

Creating high-quality and realistic images is now possible thanks to the impressive advancements in image generation. A description in natural language of your desired output is all you need to obtain breathtaking results. However, as the…

Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…

With the development of the Generative Adversarial Networks (GANs) and DeepFakes, AI-synthesized images are now of such high quality that humans can hardly distinguish them from real images. It is imperative for media forensics to develop…

A generative modeling framework is proposed that combines diffusion models and manifold learning to efficiently sample data densities on manifolds. The approach utilizes Diffusion Maps to uncover possible low-dimensional underlying (latent)…

Uncertain information is commonplace in real-world data management scenarios. The ability to represent large sets of possible instances (worlds) while supporting efficient storage and processing is an important challenge in this context.…

Deep Learning failure cases are abundant, particularly in the medical area. Recent studies in out-of-distribution generalization have advanced considerably on well-controlled synthetic datasets, but they do not represent medical imaging…

Machine learning models often fail to generalize well under distributional shifts. Understanding and overcoming these failures have led to a research field of Out-of-Distribution (OOD) generalization. Despite being extensively studied for…

Real-world text image super-resolution aims to restore overall visual quality and text legibility in images suffering from diverse degradations and text distortions. However, the scarcity of text image data in existing datasets results in…

We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Most research on robustness focuses on synthetic image perturbations (noise, simulated weather artifacts, adversarial…

This paper presents a comprehensive evaluation of instance segmentation models with respect to real-world image corruptions as well as out-of-domain image collections, e.g. images captured by a different set-up than the training dataset.…

State-of-the-art face recognition models show impressive accuracy, achieving over 99.8% on Labeled Faces in the Wild (LFW) dataset. Such models are trained on large-scale datasets that contain millions of real human face images collected…