Related papers: Err on the Side of Texture: Texture Bias on Real D…
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging. In this paper, we systematically investigate the performance of two models on datasets…
We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to…
Texture plays a vital role in enhancing visual richness in both real photographs and computer-generated imagery. However, the process of editing textures often involves laborious and repetitive manual adjustments of textons, which are the…
In recent years, machine learning algorithms have become ubiquitous in a multitude of high-stakes decision-making applications. The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to…
Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear…
State-of-the-art algorithms for many semantic visual tasks are based on the use of convolutional neural networks. These networks are commonly trained, and evaluated, on large annotated datasets of artifact-free high-quality images. In this…
Research on bias in machine learning algorithms has generally been concerned with the impact of bias on predictive accuracy. We believe that there are other factors that should also play a role in the evaluation of bias. One such factor is…
Text-to-image models produce graphic design at production scale, but their supervision comes from photo-style preference data with a single overall verdict per comparison. Designers evaluate along several distinct axes, including…
A common study area in anomaly identification is industrial images anomaly detection based on texture background. The interference of texture images and the minuteness of texture anomalies are the main reasons why many existing models fail…
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…
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…
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have…
Humans rely on properties of the materials that make up objects to guide our interactions with them. Grasping smooth materials, for example, requires care, and softness is an ideal property for fabric used in bedding. Even when these…
Image classifiers should be used with caution in the real world. Performance evaluated on a validation set may not reflect performance in the real world. In particular, classifiers may perform well for conditions that are frequently…
It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…
As AI systems become more embedded in everyday life, the development of fair and unbiased models becomes more critical. Considering the social impact of AI systems is not merely a technical challenge but a moral imperative. As evidenced in…
Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness in other stages in the ML pipeline. We contend that one…
Image aesthetics is a crucial metric in the field of image generation. However, textual aesthetics has not been sufficiently explored. With the widespread application of large language models (LLMs), previous work has primarily focused on…
Singh et al. (2020) point out the dangers of contextual bias in visual recognition datasets. They propose two methods, CAM-based and feature-split, that better recognize an object or attribute in the absence of its typical context while…
Due to implicitly introduced periodic shifting of limited searching area, visual object tracking using correlation filters often has to confront undesired boundary effect. As boundary effect severely degrade the quality of object model, it…