56 citations · 265 across the 31 of their papers we have counts for
34 papers
Gender Bias in Vision-Language In-Context Learning
Tong Xiang, Noa Garcia, Yuta Nakashima
In-context learning (ICL) enables large vision-language models (LVLMs) to perform tasks by following patterns from in-context examples, yet its potential to amplify societal biases…
Invisible Shortcuts: Why Vision Encoders Know Your Camera
Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos +2
Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals. Prior work has focused on visible biases, such as object-background or texture correl…
EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories
Lu Wei, Yuta Nakashima, Noa Garcia
The widespread adoption of text-to-image (T2I) generation has raised concerns about privacy, bias, and copyright violations. Concept erasure techniques offer a promising solution b…
Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
Yusuke Hirota, Ryo Hachiuma, Boyi Li +9
Gender bias in vision-language foundation models (VLMs) raises concerns about their safe deployment and is typically evaluated using benchmarks with gender annotations on real-worl…
Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
Ryan Ramos, Vladan Stojnić, Giorgos Kordopatis-Zilos +3
Prior work has analyzed the robustness of visual encoders to image transformations and corruptions, particularly in cases where such alterations are not seen during training. When…
No Annotations for Object Detection in Art through Stable Diffusion
Patrick Ramos, Nicolas Gonthier, Selina Khan +2
Object detection in art is a valuable tool for the digital humanities, as it allows for faster identification of objects in artistic and historical images compared to humans. Howev…
Gender Bias Evaluation in Text-to-image Generation: A Survey
Yankun Wu, Yuta Nakashima, Noa Garcia
The rapid development of text-to-image generation has brought rising ethical considerations, especially regarding gender bias. Given a text prompt as input, text-to-image models ge…
Would Deep Generative Models Amplify Bias in Future Models?
Tianwei Chen, Yusuke Hirota, Mayu Otani +2
We investigate the impact of deep generative models on potential social biases in upcoming computer vision models. As the internet witnesses an increasing influx of AI-generated im…
Towards Artwork Explanation in Large-scale Vision Language Models
Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito +2
Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clari…
Stable Diffusion Exposed: Gender Bias from Prompt to Image
Yankun Wu, Yuta Nakashima, Noa Garcia
Several studies have raised awareness about social biases in image generative models, demonstrating their predisposition towards stereotypes and imbalances. This paper contributes…
Situating the social issues of image generation models in the model life cycle: a sociotechnical approach
Amelia Katirai, Noa Garcia, Kazuki Ide +2
The race to develop image generation models is intensifying, with a rapid increase in the number of text-to-image models available. This is coupled with growing public awareness of…
CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care
Tong Xiang, Liangzhi Li, Wangyue Li +4
The recent advances in natural language processing (NLP), have led to a new trend of applying large language models (LLMs) to real-world scenarios. While the latest LLMs are astoni…
Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis
Yankun Wu, Yuta Nakashima, Noa Garcia
The duality of content and style is inherent to the nature of art. For humans, these two elements are clearly different: content refers to the objects and concepts in the piece of…
Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
Noa Garcia, Yusuke Hirota, Yankun Wu +1
The increasing tendency to collect large and uncurated datasets to train vision-and-language models has raised concerns about fair representations. It is known that even small but…
Model-Agnostic Gender Debiased Image Captioning
Yusuke Hirota, Yuta Nakashima, Noa Garcia
Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models.…
Learning More May Not Be Better: Knowledge Transferability in Vision and Language Tasks
Tianwei Chen, Noa Garcia, Mayu Otani +3
Is more data always better to train vision-and-language models? We study knowledge transferability in multi-modal tasks. The current tendency in machine learning is to assume that…
Gender and Racial Bias in Visual Question Answering Datasets
Yusuke Hirota, Yuta Nakashima, Noa Garcia
Vision-and-language tasks have increasingly drawn more attention as a means to evaluate human-like reasoning in machine learning models. A popular task in the field is visual quest…
Quantifying Societal Bias Amplification in Image Captioning
Yusuke Hirota, Yuta Nakashima, Noa Garcia
We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and…
The Met Dataset: Instance-level Recognition for Artworks
Nikolaos-Antonios Ypsilantis, Noa Garcia, Guangxing Han +3
This work introduces a dataset for large-scale instance-level recognition in the domain of artworks. The proposed benchmark exhibits a number of different challenges such as large…
Transferring Domain-Agnostic Knowledge in Video Question Answering
Tianran Wu, Noa Garcia, Mayu Otani +3
Video question answering (VideoQA) is designed to answer a given question based on a relevant video clip. The current available large-scale datasets have made it possible to formul…
Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
Zechen Bai, Yuta Nakashima, Noa Garcia
Have you ever looked at a painting and wondered what is the story behind it? This work presents a framework to bring art closer to people by generating comprehensive descriptions o…
A Picture May Be Worth a Hundred Words for Visual Question Answering
Yusuke Hirota, Noa Garcia, Mayu Otani +4
How far can we go with textual representations for understanding pictures? In image understanding, it is essential to use concise but detailed image representations. Deep visual fe…
GCNBoost: Artwork Classification by Label Propagation through a Knowledge Graph
Cheikh Brahim El Vaigh, Noa Garcia, Benjamin Renoust +3
The rise of digitization of cultural documents offers large-scale contents, opening the road for development of AI systems in order to preserve, search, and deliver cultural herita…
Understanding the Role of Scene Graphs in Visual Question Answering
Vinay Damodaran, Sharanya Chakravarthy, Akshay Kumar +5
Visual Question Answering (VQA) is of tremendous interest to the research community with important applications such as aiding visually impaired users and image-based search. In th…