Related papers: Activation-Deactivation: A General Framework for R…

Prototype-based reconstruction methods for unsupervised anomaly detection utilize a limited set of learnable prototypes which only aggregates insufficient normal information, resulting in undesirable reconstruction. However, increasing the…

Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that induce desired misclassifications in the models. Such risks impede the application of machine learning in security-sensitive domains.…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversarial attacks. While existing research has explored white-box…

As deep vision models' popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the…

Deep Learning of neural networks has gained prominence in multiple life-critical applications like medical diagnoses and autonomous vehicle accident investigations. However, concerns about model transparency and biases persist. Explainable…

Zero-shot 3D anomaly detection aims to identify anomalies without access to training data from target categories. However, existing methods mainly rely on projecting 3D observations into multi-view representations that primarily capture…

In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without seeing occlusions while being able to transfer the learned…

Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation,…

Video anomaly detection (VAD) plays a vital role in real-world applications such as security surveillance, autonomous driving, and industrial monitoring. Recent advances in large pre-trained models have opened new opportunities for…

Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are…

Deep learning methods based on Convolutional Neural Networks (CNNs) have shown great potential to improve early and accurate diagnosis of Alzheimer's disease (AD) dementia based on imaging data. However, these methods have yet to be widely…

Despite the remarkable success, recent reconstruction-based anomaly detection (AD) methods via diffusion modeling still involve fine-grained noise-strength tuning and computationally expensive multi-step denoising, leading to a fundamental…

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class…

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

To equip Convolutional Neural Networks (CNNs) with explainability, it is essential to interpret how opaque models take specific decisions, understand what causes the errors, improve the architecture design, and identify unethical biases in…

The advancements in deep learning-based methods for visual perception tasks have seen astounding growth in the last decade, with widespread adoption in a plethora of application areas from autonomous driving to clinical decision support…

Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) have only limited robustness to partial…

In the realm of human-machine interaction, artificial intelligence has become a powerful tool for accelerating data modeling tasks. Object detection methods have achieved outstanding results and are widely used in critical domains like…

Deep learning models have achieved remarkable success across diverse domains. However, the intricate nature of these models often impedes a clear understanding of their decision-making processes. This is where Explainable AI (XAI) becomes…

Interpreting the decision-making process of deep convolutional neural networks remains a central challenge in achieving trustworthy and transparent artificial intelligence. Explainable AI (XAI) techniques, particularly Class Activation Map…