Related papers: Neural Image Compression: Generalization, Robustne…
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and…
Out-of-distribution (OOD) detection is a crucial part of deploying machine learning models safely. It has been extensively studied with a plethora of methods developed in the literature. This problem is tackled with an OOD score…
Modern deep neural network models are known to erroneously classify out-of-distribution (OOD) test data into one of the in-distribution (ID) training classes with high confidence. This can have disastrous consequences for safety-critical…
Out-of-distribution (OOD) detection and lossless compression constitute two problems that can be solved by the training of probabilistic models on a first dataset with subsequent likelihood evaluation on a second dataset, where data…
This paper considers the problem of lossy neural image compression (NIC). Current state-of-the-art (sota) methods adopt uniform posterior to approximate quantization noise, and single-sample pathwise estimator to approximate the gradient of…
Since the introduction of digital and computational pathology as a field, one of the major problems in the clinical application of algorithms has been the struggle to generalize well to examples outside the distribution of the training…
Deep learned (DL) models for image recognition have been shown to fail to generalize to data from different devices, populations, etc. COVID-19 detection from Chest X-rays (CXRs), in particular, has been shown to fail to generalize to…
The ability to generalize out-of-domain (OOD) is an important goal for deep neural network development, and researchers have proposed many high-performing OOD generalization methods from various foundations. While many OOD algorithms…
There is a lot of ongoing research effort into developing different techniques for neural networks compression. However, the community lacks standardised evaluation metrics, which are key to identifying the most suitable compression…
Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…
Improving out-of-distribution (OOD) generalization during in-distribution (ID) adaptation is a primary goal of robust fine-tuning of zero-shot models beyond naive fine-tuning. However, despite decent OOD generalization performance from…
Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks, particularly due to overconfident predictions on unseen OOD samples during testing. We reveal a key insight: OOD samples predicted as the same…
We present OpenICS, an image compressive sensing toolbox that includes multiple image compressive sensing and reconstruction algorithms proposed in the past decade. Due to the lack of standardization in the implementation and evaluation of…
Existing works show that although modern neural networks achieve remarkable generalization performance on the in-distribution (ID) dataset, the accuracy drops significantly on the out-of-distribution (OOD) datasets \cite{recht2018cifar,…
In AI-driven medical imaging, the failure to detect out-of-distribution (OOD) data poses a severe risk to clinical reliability, potentially leading to critical diagnostic errors. Current OOD detection methods often demand impractical…
When deployed for risk-sensitive tasks, deep neural networks must be able to detect instances with labels from outside the distribution for which they were trained. In this paper we present a novel framework to benchmark the ability of…
Algorithms for learning programmatic representations for sequential decision-making problems are often evaluated on out-of-distribution (OOD) problems, with the common conclusion that programmatic policies generalize better than neural…
Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise, their susceptibility to out-of-distribution (OOD)…
In the open world, detecting out-of-distribution (OOD) data, whose labels are disjoint with those of in-distribution (ID) samples, is important for reliable deep neural networks (DNNs). To achieve better detection performance, one type of…
We propose a simple modification to standard ResNet architectures--L2 normalization over feature space--that substantially improves out-of-distribution (OoD) performance on the previously proposed Deep Deterministic Uncertainty (DDU)…