Related papers: Exposing and Correcting the Gender Bias in Image C…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextual diversity. In reality, each object or attribute within a…

Image captioning is a research hotspot where encoder-decoder models combining convolutional neural network (CNN) and long short-term memory (LSTM) achieve promising results. Despite significant progress, these models generate sentences…

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…

While understanding and removing gender biases in language models has been a long-standing problem in Natural Language Processing, prior research work has primarily been limited to English. In this work, we investigate some of the…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…

Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotated pairs of images…

The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias,…

Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To…

Describing images with text is a fundamental problem in vision-language research. Current studies in this domain mostly focus on single image captioning. However, in various real applications (e.g., image editing, difference interpretation,…

Image captioning models require the high-level generalization ability to describe the contents of various images in words. Most existing approaches treat the image-caption pairs equally in their training without considering the differences…

The gender bias present in the data on which language models are pre-trained gets reflected in the systems that use these models. The model's intrinsic gender bias shows an outdated and unequal view of women in our culture and encourages…

With the advancements in Large Language and Latent Diffusion models, brain decoding has achieved remarkable results in recent years. The works on the NSD dataset, with stimuli images from the COCO dataset, leverage the embeddings from the…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Image captioning is a computer vision task that involves generating natural language descriptions for images. This method has numerous applications in various domains, including image retrieval systems, medicine, and various industries.…

In this work, we study idiosyncrasies in the caption models and their downstream impact on text-to-image models. We design a systematic analysis: given either a generated caption or the corresponding image, we train neural networks to…

Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports suggest that these systems may produce biased results, discriminating against people in…

We explore the extent to which zero-shot vision-language models exhibit gender bias for different vision tasks. Vision models traditionally required task-specific labels for representing concepts, as well as finetuning; zero-shot models…

Image captioning is one of the most challenging tasks in AI, which aims to automatically generate textual sentences for an image. Recent methods for image captioning follow encoder-decoder framework that transforms the sequence of salient…

Face gender classification models often reflect and amplify demographic biases present in their training data, leading to uneven performance across gender and racial subgroups. We introduce pseudo-balancing, a simple and effective strategy…