AIConfPaper
← Search

Andreas Dengel

8 accepted papers

2026

When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

Krzysztof Adamkiewicz, Brian B. Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel
CVPR 2026

Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a

Cited by 0Source ↗Scholar ↗
2026

YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction

Miro Miranda, Deepak Pathak, Patrick Helber, Benjamin Bischke, Hiba Najjar, Francisco Mena +7
CVPR 2026

Crop yield prediction requires substantial data to train scalable models. However, creating yield prediction datasets is constrained by high acquisition costs, heterogeneous data quality, and data privacy regulations. Consequently, existing datasets are scarce, low in quality, or limited to regional

Cited by 0Source ↗code ↗Scholar ↗
2025

TKG-DM: Training-free Chroma Key Content Generation Diffusion Model

Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Takahiro Shirakawa, Ko Watanabe, Andreas Dengel +1
CVPR 2025highlight

Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their abili…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Unlocking Dataset Distillation with Diffusion Models

Brian Bernhard Moser, Federico Raue, Sebastian Palacio, Stanislav Frolov, Andreas Dengel
NeurIPS 2025spotlight

Dataset distillation seeks to condense datasets into smaller but highly representative synthetic samples. While diffusion models now lead all generative benchmarks, current distillation methods avoid them and rely instead on GANs or autoencoders, or, at best, sampling from a fixed diffusion prior.…

Cited by 0Source ↗code ↗Scholar ↗
2023

Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving

Abdul Hannan Khan, Mohammed Shariq Nawaz, Andreas Dengel
CVPR 2023poster

Autonomous driving systems rely heavily on the underlying perception module which needs to be both performant and efficient to allow precise decisions in real-time. Avoiding collisions with pedestrians is of topmost priority in any autonomous driving system. Therefore, pedestrian detection is one of…

Cited by 37Source ↗PDF ↗Scholar ↗
2022

Search and Learn: Improving Semantic Coverage for Data-to-Text Generation

Shailza Jolly, Zi Xuan Zhang, Andreas Dengel, Lili Mou
AAAI 2022technical

Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learning the correspondence between tables and texts. However, large training sets are expensive to obtain, limiting the appl…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2018

What Do Deep Networks Like to See?

Sebastian Palacio, Joachim Folz, Jörn Hees, Federico Raue, Damian Borth, Andreas Dengel
CVPR 2018poster

We propose a novel way to measure and understand convolutional neural networks by quantifying the amount of input signal they let in. To do this, an autoencoder (AE) was fine-tuned on gradients from a pre-trained classifier with fixed parameters. We compared the reconstructed samples from AEs that w…

Cited by 41Source ↗PDF ↗code ↗Scholar ↗