6 papers · 1 filter
What is Adversarial Training for Diffusion Models?
Briglia Maria Rosaria, Mujtaba Hussain Mirza, Giuseppe Lisanti +1
We answer the question in the title, showing that adversarial training (AT) for diffusion models (DMs) fundamentally differs from classifiers: while AT in classifiers enforces outp…
Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense
Filippo Bartolucci, Iacopo Masi, Giuseppe Lisanti
Image manipulation detection and localization have received considerable attention from the research community given the blooming of Generative Models (GMs). Detection methods that…
Semantic Image Synthesis via Class-Adaptive Cross-Attention
Tomaso Fontanini, Claudio Ferrari, Giuseppe Lisanti +2
In semantic image synthesis the state of the art is dominated by methods that use customized variants of the SPatially-Adaptive DE-normalization (SPADE) layers, which allow for goo…
Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation
Nico Giambi, Giuseppe Lisanti
Deep generative models have shown impressive results in generating realistic images of faces. GANs managed to generate high-quality, high-fidelity images when conditioned on semant…
Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding
Giuseppe Lisanti, Niki Martinel, Alberto Del Bimbo +1
Person re-identification is best known as the problem of associating a single person that is observed from one or more disjoint cameras. The existing literature has mainly addresse…
Context-Aware Trajectory Prediction
Federico Bartoli, Giuseppe Lisanti, Lamberto Ballan +1
Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might b…