Related papers: When categorization-based stranger avoidance expla…
In automated driving, object detection is crucial for perceiving the environment. Although deep learning-based detectors offer high performance, their black-box nature complicates safety assurance. We propose a novel methodology to analyze…
The high level of photorealism in state-of-the-art diffusion models like Midjourney, Stable Diffusion, and Firefly makes it difficult for untrained humans to distinguish between real photographs and AI-generated images. To address this…
The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle…
Data-driven methods that detect anomalies in times series data are ubiquitous in practice, but they are in general unable to provide helpful explanations for the predictions they make. In this work we propose a model-agnostic algorithm that…
Developing AI systems with a human-like understanding of everyday concepts is a key step towards developing safe, reliable systems whose behavior makes sense to humans. When probing concept understanding, asking questions about plausible…
Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. The complexity of the task arises from the commonly-adopted definition of an abnormal event, that is, a rarely…
Virtual re-creations of real-world places are attractive and becoming more popular. Attractiveness of re-created place is commonly determined by the degree of visual similarity to the original places. Even if the re-creation has poor…
The human visual system contains a hierarchical sequence of modules that take part in visual perception at different levels of abstraction, i.e., superordinate, basic, and subordinate levels. One important question is to identify the…
Latest research revealed a considerable lack of reliability within user feedback and discussed striking impacts for the assessment of adaptive web systems and content personalisation approaches, e.g. ranking errors, systematic biases to…
Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal…
Anomaly detection at scale is an extremely challenging problem of great practicality. When data is large and high-dimensional, it can be difficult to detect which observations do not fit the expected behaviour. Recent work has coalesced on…
The human visual system is well-tuned to detect faces of all shapes and sizes. While this brings obvious survival advantages, such as a better chance of spotting unknown predators in the bush, it also leads to spurious face detections.…
Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that (to the untrained eye) are indistinguishable from real images. Deepfakes are produced by algorithms that learn to distinguish between…
Predicting human perceptual similarity is a challenging subject of ongoing research. The visual process underlying this aspect of human vision is thought to employ multiple different levels of visual analysis (shapes, objects, texture,…
We present a technique for estimating the similarity between objects such as movies or foods whose proper representation depends on human perception. Our technique combines a modest number of human similarity assessments to infer a pairwise…
Human beings prefer ordered complexity and not randomness in their environment, a result of our perceptual system evolving to interpret natural forms. We also recognize monotonously repeating forms as unnatural. Although widespread in…
While reinforcement learning (RL) algorithms have been successfully applied to numerous tasks, their reliance on neural networks makes their behavior difficult to understand and trust. Counterfactual explanations are human-friendly…
We introduce to VR a novel imperceptible gaze guidance technique from a recent discovery that human gaze can be attracted to a cue that contrasts from the background in its perceptually non-distinctive ocularity, defined as the relative…
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. While there do exist…
When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space of the data manifold. To provide evidence for this…