Related papers: DECIDER: Leveraging Foundation Model Priors for Im…

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…

Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification…

Reliable failure detection holds paramount importance in safety-critical applications. Yet, neural networks are known to produce overconfident predictions for misclassified samples. As a result, it remains a problematic matter as existing…

Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…

Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising…

Understanding material failure is critical for designing stronger and lighter structures by identifying weaknesses that could be mitigated. Existing full-physics numerical simulation techniques involve trade-offs between speed, accuracy,…

Constructing assurance cases is a widely used, and sometimes required, process toward demonstrating that safety-critical systems will operate safely in their planned environment. To mitigate the risk of errors and missing edge cases, the…

Recent advancements in Vision-Language Models (VLMs) have enabled complex multimodal tasks by processing text and image data simultaneously, significantly enhancing the field of artificial intelligence. However, these models often exhibit…

There is a fundamental limitation in the prediction performance that a machine learning model can achieve due to the inevitable uncertainty of the prediction target. In classification problems, this can be characterized by the Bayes error,…

Text-based visual descriptors--ranging from simple class names to more descriptive phrases--are widely used in visual concept discovery and image classification with vision-language models (VLMs). Their effectiveness, however, depends on a…

Despite the remarkable multimodal capabilities of Large Vision-Language Models (LVLMs), discrepancies often occur between visual inputs and textual outputs--a phenomenon we term visual hallucination. This critical reliability gap poses…

We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework which enables Large Language Models to autonomously improve their problem-solving capabilities through self-guided learning by recursively…

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Face recognition systems are increasingly vulnerable to morphing attacks, where a composite image is crafted to match multiple identities, enabling unauthorized access and identity fraud. Existing detection methods identify morphed images…

Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning…

Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from their default System 1 processing, which is fast and…

We develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data. Our model is interpretable and is able to provide a…

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to…

Machine-vision-based defect classification techniques have been widely adopted for automatic quality inspection in manufacturing processes. This article describes a general framework for classifying defects from high volume data batches…

This work is addressing the problem of defect anomaly detection based on a clean reference image. Specifically, we focus on SEM semiconductor defects in addition to several natural image anomalies. There are well-known methods to create a…