Related papers: ConceptScope: Characterizing Dataset Bias via Dise…

We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior…

Object recognition is among the fundamental tasks in the computer vision applications, paving the path for all other image understanding operations. In every stage of progress in object recognition research, efforts have been made to…

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…

The semantic gap is defined as the difference between the linguistic representations of the same concept, which usually leads to misunderstanding between individuals with different knowledge backgrounds. Since linguistically annotated…

Concepts are key building blocks of higher level human understanding. Explainable AI (XAI) methods have shown tremendous progress in recent years, however, local attribution methods do not allow to identify coherent model behavior across…

State-of-the-art empirical work has shown that visual representations learned by deep neural networks are robust in nature and capable of performing classification tasks on diverse datasets. For example, CLIP demonstrated zero-shot transfer…

This paper addresses the often overlooked issue of fairness in the autonomous driving domain, particularly in vision-based perception and prediction systems, which play a pivotal role in the overall functioning of Autonomous Vehicles (AVs).…

Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often…

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models'…

A biased dataset is a dataset that generally has attributes with an uneven class distribution. These biases have the tendency to propagate to the models that train on them, often leading to a poor performance in the minority class. In this…

Machine learning models are known to perpetuate and even amplify the biases present in the data. However, these data biases frequently do not become apparent until after the models are deployed. Our work tackles this issue and enables the…

Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between…

Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information that is useful for downstream tasks. We hypothesize that the embedding space can be disentangled to separate the information on…

Multimodal AI models capable of associating images and text hold promise for numerous domains, ranging from automated image captioning to accessibility applications for blind and low-vision users. However, uncertainty about bias has in some…

Subspace clustering algorithms are used for understanding the cluster structure that explains the dataset well. These methods are extensively used for data-exploration tasks in various areas of Natural Sciences. However, most of these…

Modern face recognition models embed identities on a unit hypersphere, where identity variation forms tight clusters. Conversely, shared semantic attributes can often be effectively approximated as linear directions in the latent space.…

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic…

We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas, where each image…

In the last few years, Artificial Intelligence systems have become increasingly widespread. Unfortunately, these systems can share many biases with human decision-making, including demographic biases. Often, these biases can be traced back…