相关论文: DASH: Visual Analytics for Debiasing Image Classif…

The goal of visual analytics is to create a symbiosis between human and computer by leveraging their unique strengths. While this model has demonstrated immense success, we are yet to realize the full potential of such a human-computer…

Since its beginning visual recognition research has tried to capture the huge variability of the visual world in several image collections. The number of available datasets is still progressively growing together with the amount of samples…

Although the availability of a large amount of data is usually given for granted, there are relevant scenarios where this is not the case; for instance, in the biomedical/healthcare domain, some applications require to build huge datasets…

Anomaly detection remains an open challenge in many application areas. While there are a number of available machine learning algorithms for detecting anomalies, analysts are frequently asked to take additional steps in reasoning about the…

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…

Cognitive biases have been shown to lead to faulty decision-making. Recent research has demonstrated that the effect of cognitive biases, anchoring bias in particular, transfers to information visualization and visual analytics. However, it…

New medical datasets are now more open to the public, allowing for better and more extensive research. Although prepared with the utmost care, new datasets might still be a source of spurious correlations that affect the learning process.…

In recent years, Face Anti-Spoofing (FAS) has played a crucial role in preserving the security of face recognition technology. With the rise of counterfeit face generation techniques, the challenge posed by digitally edited faces to face…

Galaxy morphologies and their relation with physical properties have been a relevant subject of study in the past. Most galaxy morphology catalogs have been labelled by human annotators or by machine learning models trained on human…

Existing facial analysis systems have been shown to yield biased results against certain demographic subgroups. Due to its impact on society, it has become imperative to ensure that these systems do not discriminate based on gender,…

Modern computer vision applications rely on learning-based perception modules parameterized with neural networks for tasks like object detection. These modules frequently have low expected error overall but high error on atypical groups of…

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…

The collection of large, complex datasets has become common across a wide variety of domains. Visual analytics tools increasingly play a key role in exploring and answering complex questions about these large datasets. However, many…

Change detection visual question answering (CDVQA) requires answering text queries by reasoning about semantic changes in bi-temporal remote sensing images. A straightforward approach is to boost CDVQA performance with generic…

Fairness is crucial when training a deep-learning discriminative model, especially in the facial domain. Models tend to correlate specific characteristics (such as age and skin color) with unrelated attributes (downstream tasks), resulting…

Standard lossy image compression algorithms aim to preserve an image's appearance, while minimizing the number of bits needed to transmit it. However, the amount of information actually needed by a user for downstream tasks -- e.g.,…

The characteristics of feature selection, nonlinear combination and multi-task auxiliary learning mechanism of the human visual perception system play an important role in real-world scenarios, but the research of image fusion theory based…

Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to…

There is limited understanding of the information captured by deep spatiotemporal models in their intermediate representations. For example, while evidence suggests that action recognition algorithms are heavily influenced by visual…

Bias is known to be an impediment to fair decisions in many domains such as human resources, the public sector, health care etc. Recently, hope has been expressed that the use of machine learning methods for taking such decisions would…