4 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…
From Global to Local: Social Bias Transfer in CLIP
Ryan Ramos, Yusuke Hirota, Yuta Nakashima +1
The recycling of contrastive language-image pre-trained (CLIP) models as backbones for a large number of downstream tasks calls for a thorough analysis of their transferability imp…
Data Leakage in Visual Datasets
Patrick Ramos, Ryan Ramos, Noa Garcia
We analyze data leakage in visual datasets. Data leakage refers to images in evaluation benchmarks that have been seen during training, compromising fair model evaluation. Given th…