Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions

Recent advances in generative AI have enabled visual content creation through text-to-image (T2I) generation. However, despite their creative potential, T2I models often replicate and amplify societal stereotypes -- particularly those related to gender, race, and culture -- raising important ethical concerns. This paper proposes a theory-driven bias detection rubric and a Social Stereotype Index (SSI) to systematically evaluate social biases in T2I outputs. We audited three major T2I model outputs -- DALL-E-3, Midjourney-6.1, and Stability AI Core -- using 100 queries across three categories -- geocultural, occupational, and adjectival. Our analysis reveals that initial outputs are prone to include stereotypical visual cues, including gendered professions, cultural markers, and western beauty norms. To address this, we adopted our rubric to conduct targeted prompt refinement using LLMs, which significantly reduced bias -- SSI dropped by 61% for geocultural, 69% for occupational, and 51% for adjectival queries. We complemented our quantitative analysis through a user study examining perceptions, awareness, and preferences around AI-generated biased imagery. Our findings reveal a key tension -- although prompt refinement can mitigate stereotypes, it can limit contextual alignment. Interestingly, users often perceived stereotypical images to be more aligned with their expectations. We discuss the need to balance ethical debiasing with contextual relevance and call for T2I systems that support global diversity and inclusivity while not compromising the reflection of real-world social complexity.

Switched auxiliary loss for robust training of transformer models for histopathological image segmentation

Functional tissue Units (FTUs) are cell population neighborhoods local to a particular organ performing its main function. The FTUs provide crucial information to the pathologist in understanding the disease affecting a particular organ by providing information at the cellular level. In our research, we have developed a model to segment multi-organ FTUs across 5 organs namely: the kidney, large intestine, lung, prostate and spleen by utilizing the HuBMAP + HPA - Hacking the Human Body competition dataset. We propose adding shifted auxiliary loss for training models like the transformers to overcome the diminishing gradient problem which poses a challenge towards optimal training of deep models. Overall, our model achieved a dice score of 0.793 on the public dataset and 0.778 on the private dataset and shows a 1% improvement with the use of the proposed method. The findings also bolster the use of transformers models for dense prediction tasks in the field of medical image analysis. The study assists in understanding the relationships between cell and tissue organization thereby providing a useful medium to look at the impact of cellular functions on human health.

Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing

Environmental damage has been of much concern, particularly coastal areas and the oceans given climate change and drastic effects of pollution and extreme climate events. Our present day analytical capabilities along with the advancements in information acquisition techniques such as remote sensing can be utilized for the management and study of coral reef ecosystems. In this paper, we present Reef-insight, an unsupervised machine learning framework that features advanced clustering methods and remote sensing for reef community mapping. Our framework compares different clustering methods to evaluate them for reef community mapping using remote sensing data. We evaluate four major clustering approaches such as k- means, hierarchical clustering, Gaussian mixture model, and density-based clustering based on qualitative and visual assessment. We utilise remote sensing data featuring Heron reef island region in the Great Barrier Reef of Australia. Our results indicate that clustering methods using remote sensing data can well identify benthic and geomorphic clusters that are found in reefs when compared to other studies. Our results indicate that Reef-insight can generate detailed reef community maps outlining distinct reef habitats and has the potential to enable further insights for reef restoration projects. We release our framework as open source software to enable its extension to different parts of the world