6 papers
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…
Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
Ryan Ramos, Vladan StojniÄ, 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…
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…
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…
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…
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…