← Search

Federico Raue

5 accepted papers

2026

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

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 0SourceScholar
2025

Unlocking Dataset Distillation with Diffusion Models

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 0SourcecodeScholar
2018

What Do Deep Networks Like to See?

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…

2015

Scene Labeling With LSTM Recurrent Neural Networks

CVPR 2015poster

This paper addresses the problem of pixel-level segmentation and classification of scene images with an entirely learning-based approach using Long Short Term Memory (LSTM) recurrent neural networks, which are commonly used for sequence classification. We investigate two-dimensional (2D) LSTM networ…

Cited by 514SourcePDFScholar