Related papers: Countering Inconsistent Labelling by Google's Visi…

Existing neural networks for computer vision tasks are vulnerable to adversarial attacks: adding imperceptible perturbations to the input images can fool these methods to make a false prediction on an image that was correctly predicted…

Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by…

This paper investigates a novel algorithmic vulnerability when imperceptible image layers confound multiple vision models into arbitrary label assignments and captions. We explore image preprocessing methods to introduce stealth…

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…

Image captioning (IC) systems, which automatically generate a text description of the salient objects in an image (real or synthetic), have seen great progress over the past few years due to the development of deep neural networks. IC plays…

Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

As Vision-Language Models (VLMs) are increasingly deployed in split-DNN configurations--with visual encoders (e.g., ResNet, ViT) operating on user devices and sending intermediate features to the cloud--there is a growing privacy risk from…

Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…

In current navigating platforms, the user's orientation is typically estimated based on the difference between two consecutive locations. In other words, the orientation cannot be identified until the second location is taken. This…

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance…

When captioning an image, people describe objects in diverse ways, such as by using different terms and/or including details that are perceptually noteworthy to them. Descriptions can be especially unique across languages and cultures.…

Classification is a major tool of statistics and machine learning. A classification method first processes a training set of objects with given classes (labels), with the goal of afterward assigning new objects to one of these classes. When…

Image captioning is a research area of immense importance, aiming to generate natural language descriptions for visual content in the form of still images. The advent of deep learning and more recently vision-language pre-training…

Matching cross-view images is challenging because the appearance and viewpoints are significantly different. While low-level features based on gradient orientations or filter responses can drastically vary with such changes in viewpoint,…

Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less…

Historical maps provide valuable information and knowledge about the past. However, as they often feature non-standard projections, hand-drawn styles, and artistic elements, it is challenging for non-experts to identify and interpret them.…

The field of Explainable Artificial Intelligence (XAI) aims to improve the interpretability of black-box machine learning models. Building a heatmap based on the importance value of input features is a popular method for explaining the…

Heatmaps are widely used to interpret deep neural networks, particularly for computer vision tasks, and the heatmap-based explainable AI (XAI) techniques are a well-researched topic. However, most studies concentrate on enhancing the…

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to…