Related papers: On Background Bias of Post-Hoc Concept Embeddings …

Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep learning models are increasingly used to make important…

Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically by estimating a simplified causal structure of the model. In existing work, this causal…

The PandaX dark matter detection project searches for dark matter particles using the technology of dual phase xenon time projection chamber. The low expected rate of the signal events makes the control of backgrounds crucial for the…

Contributions of recent deep-neural-network (DNN) based techniques have been playing a significant role in human-computer interaction (HCI) and user interface (UI) domains. One of the commonly used DNNs is human pose estimation. This kind…

Recent work has proposed the concept of backdoor attacks on deep neural networks (DNNs), where misbehaviors are hidden inside "normal" models, only to be triggered by very specific inputs. In practice, however, these attacks are difficult…

In recent years, neural networks have continued to flourish, achieving high efficiency in detecting relevant objects in photos or simply recognizing (classifying) these objects - mainly using CNN networks. Current solutions, however, are…

Concept Bottleneck Models (CBMs) map the inputs onto a set of interpretable concepts (``the bottleneck'') and use the concepts to make predictions. A concept bottleneck enhances interpretability since it can be investigated to understand…

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying…

Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both…

Recently, deep learning approaches have achieved promising results in various fields of computer vision. In this paper, we tackle the problem of head pose estimation through a Convolutional Neural Network (CNN). Differently from other…

Action recognition is also key for applications ranging from robotics to healthcare monitoring. Action information can be extracted from the body pose and movements, as well as from the background scene. However, the extent to which deep…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…

Explainable artificial intelligence (XAI) aims to help uncover flaws in an AI model's internal representations. But do people draw the right conclusions from its explanations? Specifically, do they recognize an AI's inability to distinguish…

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…

In this article we use the Natural Scenes Dataset (NSD) to train a family of feature-weighted receptive field neural encoding models. These models use a pre-trained vision or text backbone and map extracted features to the voxel space via…

Deep learning has transformed visual data analysis, with Convolutional Neural Networks (CNNs) becoming highly effective in learning meaningful feature representations directly from images. Unlike traditional manual feature engineering…

Deep artificial neural networks (DNNs) trained through backpropagation provide effective models of the mammalian visual system, accurately capturing the hierarchy of neural responses through primary visual cortex to inferior temporal cortex…

Vehicle tracking task plays an important role on the internet of vehicles and intelligent transportation system. Beyond the traditional GPS sensor, the image sensor can capture different kinds of vehicles, analyze their driving situation…

Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This…

Object detection in aerial images is an important task in environmental, economic, and infrastructure-related tasks. One of the most prominent applications is the detection of vehicles, for which deep learning approaches are increasingly…