相关论文: No Classification without Representation: Assessin…

A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a…

Existing machine learning models have proven to fail when it comes to their performance for minority groups, mainly due to biases in data. In particular, datasets, especially social data, are often not representative of minorities. In this…

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…

Image geolocation is a critical task in various image-understanding applications. However, existing methods often fail when analyzing challenging, in-the-wild images. Inspired by the exceptional background knowledge of multimodal language…

Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, it does not fulfill the closed world assumption of…

Latency to end-users and regulatory requirements push large companies to build data centers all around the world. The resulting data is "born" geographically distributed. On the other hand, many machine learning applications require a…

Image classification in the open-world must handle out-of-distribution (OOD) images. Systems should ideally reject OOD images, or they will map atop of known classes and reduce reliability. Using open-set classifiers that can reject OOD…

Semantic segmentation of land cover classes is fundamental for agricultural and economic development work, from sustainable forestry to urban planning, yet existing training datasets have significant limitations. To generate an open and…

Data-driven algorithms are only as good as the data they work with, while data sets, especially social data, often fail to represent minorities adequately. Representation Bias in data can happen due to various reasons ranging from…

Convolutional Neural Networks are a well-known staple of modern image classification. However, it can be difficult to assess the quality and robustness of such models. Deep models are known to perform well on a given training and estimation…

Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a full knowledge of the input and label spaces, making failures…

In this paper, we analyze different methods to mitigate inherent geographical biases present in state of the art image classification models. We first quantitatively present this bias in two datasets - The Dollar Street Dataset and…

Advances in Artificial Intelligence are challenged by the biases rooted in the datasets used to train the models. In image geolocation estimation, models are mostly trained using data from specific geographic regions, notably the Western…

Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract and disputed social constructs. Dataset curators frequently employ value-laden terms such as diversity, bias, and quality to characterize datasets.…

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in…

High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed on the zebra crossing…

More than half of the world's roads lack adequate street addressing systems. Lack of addresses is even more visible in daily lives of people in developing countries. We would like to object to the assumption that having an address is a…

Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the representations of…

We introduce a new landmark recognition dataset, which is created with a focus on fair worldwide representation. While previous work proposes to collect as many images as possible from web repositories, we instead argue that such approaches…

In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…