From the 1 of 15 linked papers with an AI index.
15 papers
When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov +3
The paper evaluates modern text-to-image diffusion models as sources of synthetic training data and finds that, despite higher visual quality, newer models produce less diverse ima…
LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
Tobias Christian Nauen, Anosh Billimoria, Federico Raue +3
Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the b…
ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions
Tobias Christian Nauen, Brian Moser, Federico Raue +2
Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific contex…
The Gentle Collapse: Distributional Metrics for Continual Learning
Ahmed Anwar, Andreas Wagner, Federico Raue +2
Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapse…
OA-CutMix: Correcting the Label Bias of CutMix
Tobias Christian Nauen, Stanislav Frolov, Federico Raue +2
CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic co…
TextTeacher: What Can Language Teach About Images?
Tobias Christian Nauen, Stanislav Frolov, Brian Bernhard Moser +3
The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can…