Related papers: Extending Class Activation Mapping Using Gaussian …

Deep reinforcement learning has achieved great strides in solving challenging motion control tasks. Recently, there has been significant work on methods for exploiting the data gathered during training, but there has been less work on how…

We present a new model, training procedure and architecture to create precise maps of distinction between two classes of images. The objective is to comprehend, in pixel-wise resolution, the unique characteristics of a class. These maps can…

In this paper, we develop a high-dimensional map building technique that incorporates raw pixelated semantic measurements into the map representation. The proposed technique uses Gaussian Processes (GPs) multi-class classification for map…

Vision Transformers (ViTs) achieve strong performance in visual recognition, yet their decision-making remains difficult to interpret. We propose BiCAM, a bidirectional class activation mapping method that captures both supportive…

Explainable Deep Learning has gained significant attention in the field of artificial intelligence (AI), particularly in domains such as medical imaging, where accurate and interpretable machine learning models are crucial for effective…

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus…

The analysis of expression and facial Action Units (AUs) detection are very important tasks in fields of computer vision and Human Computer Interaction (HCI) due to the wide range of applications in human life. Many works has been done…

Class Activation Mapping (CAM) is a powerful technique used to understand the decision making of Convolutional Neural Network (CNN) in computer vision. Recently, there have been attempts not only to generate better visual explanations, but…

We propose an active learning method for discovering low-dimensional structure in high-dimensional Gaussian process (GP) tasks. Such problems are increasingly frequent and important, but have hitherto presented severe practical…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network…

Visual quality inspection systems, crucial in sectors like manufacturing and logistics, employ computer vision and machine learning for precise, rapid defect detection. However, their unexplained nature can hinder trust, error…

Machine learning models are widely regarded as a way forward to tackle multi-query challenges that arise once expensive black-box simulations such as computational fluid dynamics are investigated. However, ensuring the desired level of…

Understanding the decisions of deep learning (DL) models is essential for the acceptance of DL to risk-sensitive applications. Although methods, like class activation maps (CAMs), give a glimpse into the black box, they do miss some crucial…

Representation learning in recent years has been addressed with self-supervised learning methods. The input data is augmented into two distorted views and an encoder learns the representations that are invariant to distortions -- cross-view…

Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Different activation functions work best for different deep learning models. To exploit this, we leverage recent advancements in gradient-based search techniques for neural architectures to efficiently identify high-performing activation…

Reinforcement learning provides a framework for learning to control which actions to take towards completing a task through trial-and-error. In many applications observing interactions is costly, necessitating sample-efficient learning. In…

The field of visual localization has been researched for several decades and has meanwhile found many practical applications. Despite the strong progress in this field, there are still challenging situations in which established methods…