5 papers
LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance
Jae Myung Kim, Stephan Alaniz, Cordelia Schmid +1
Despite recent advances in text-to-image generation, using synthetically generated data seldom brings a significant boost in performance for supervised learning. Oftentimes, synthe…
Feasibility with Language Models for Open-World Compositional Zero-Shot Learning
Jae Myung Kim, Stephan Alaniz, Cordelia Schmid +1
Humans can easily tell if an attribute (also called state) is realistic, i.e., feasible, for an object, e.g. fire can be hot, but it cannot be wet. In Open-World Compositional Zero…
Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data
Yiwen Liu, Jessica Bader, Jae Myung Kim
With the development of photorealistic diffusion models, models trained in part or fully on synthetic data achieve progressively better results. However, diffusion models still rou…
Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models
Nishad Singhi, Jae Myung Kim, Karsten Roth +1
Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allow…
DataDream: Few-shot Guided Dataset Generation
Jae Myung Kim, Jessica Bader, Stephan Alaniz +2
While text-to-image diffusion models have been shown to achieve state-of-the-art results in image synthesis, they have yet to prove their effectiveness in downstream applications.…