Search

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 is associated with a caption containing a pronoun relationship of subjects and objects in the scene. VisoGender is balanced by gender representation in professional roles, supporting bias evaluation in two ways: i) resolution bias, where we evaluate the difference between pronoun resolution accuracies for image subjects with gender presentations perceived as masculine versus feminine by human annotators and ii) retrieval bias, where we compare ratios of professionals perceived to have masculine and feminine gender presentations retrieved for a gender-neutral search query. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes. While the direction and magnitude of gender bias depends on the task and the model being evaluated, captioning models are generally less biased than Vision-Language Encoders. Dataset and code are available at https://github.com/oxai/visogender, Comment: NeurIPS Datasets and Benchmarks 2023. Data and code available at https://github.com/oxai/visogender

Monitoring the process is crucial for ensuring high quality in wood-based panel production. Interest in the distribution of resin in fibers and particles has increased during the last couple of decades. This study considered the potential to determine urea formaldehyde (UF) resin content in fiber mat using near-infrared (NIR) spectroscopy. Fiber mats with various resin contents were investigated with NIR combined with the partial least squares (PLS) regression and root mean square error of calibration and validation (RMSECV). The external factors, such as the distance between the fiber optic probe and the sample surface and light sources, were also evaluated. The results showed that this technique can sufficiently determine the resin content in the resinous fiber mat with accuracy of up to 95%. The light sources and the distances from the probe to the surface did not significantly influence the discrimination and prediction of resin content.

Monitoring the process is crucial for ensuring high quality in wood-based panel production. Interest in the distribution of resin in fibers and particles has increased during the last couple of decades. This study considered the potential to determine urea formaldehyde (UF) resin content in fiber mat using near-infrared (NIR) spectroscopy. Fiber mats with various resin contents were investigated with NIR combined with the partial least squares (PLS) regression and root mean square error of calibration and validation (RMSECV). The external factors, such as the distance between the fiber optic probe and the sample surface and light sources, were also evaluated. The results showed that this technique can sufficiently determine the resin content in the resinous fiber mat with accuracy of up to 95%. The light sources and the distances from the probe to the surface did not significantly influence the discrimination and prediction of resin content.

[THIS IS AN UNDERGRADUATE PROJECT] This paper discusses the effectiveness of the bug finder based on "micro-grammar"., Comment: 4 pages