43 citations · 90 across the 21 of their papers we have counts for
23 papers
FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models
Zahra Dehghani, Pablo Piantanida, Mohammadhadi Shateri
Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on the number of function evalua…
Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning
Zahra Dehghani, Pablo Piantanida, Mohammadhadi Shateri
Class unlearning aims to remove a model's ability to recognize designated forget classes while preserving performance on retain classes. However, low forget accuracy after unlearni…
Continuous Adversarial MeanFlow for Few-Step Generative Adaptation from Any Parameterization
Yara Bahram, Zahra Dehghani, Mélodie Desbos +3
Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model leaves its costly multi-step sam…
A Production-Oriented Framework for Evaluation of SFX Generation
Mélodie Desbos, Yara Bahram, Eric Granger +1
Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable vari…
Selective Prediction Forgetting for Adaptation of Weakly Supervised Localization of Histology Images
Alexis Guichemerre, Banafsheh Karimian, Soufiane Belharbi +6
Under strong cross-domain shifts, weakly supervised object localization (WSOL) models often lose their capacity to discriminate and develop a strong prediction bias toward a subset…
Longitudinal Risk Prediction in Mammography with Privileged History Distillation
Banafsheh Karimian, Soufiane Belharbi, Alexis Guichemerre +3
Longitudinal mammography screening has become an important source of information for improving future breast cancer risk prediction. However, the performance of current longitudina…
Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri +1
Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within the…
Learning Task-Agnostic Representations through Multi-Teacher Distillation
Philippe Formont, Maxime Darrin, Banafsheh Karimian +5
Casting complex inputs into tractable representations is a critical step across various fields. Diverse embedding models emerge from differences in architectures, loss functions, i…
DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion Models
Yara Bahram, Mohammadhadi Shateri, Eric Granger
Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods he…
CLIP-IT: CLIP-based Pairing for Histology Images Classification
Banafsheh Karimian, Giulia Avanzato, Soufian Belharbi +4
Multimodal learning has shown promise in medical imaging, combining complementary modalities like images and text. Vision-language models (VLMs) capture rich diagnostic cues but of…
PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization
Alexis Guichemerre, Soufiane Belharbi, Mohammadhadi Shateri +2
Weakly supervised object localization (WSOL) methods allow training models to classify images and localize ROIs. WSOL only requires low-cost image-class annotations yet provides a…
MTLoc: A Confidence-Based Source-Free Domain Adaptation Approach For Indoor Localization
Negar Mehregan, Berk Bozkurt, Eric Granger +2
Various deep learning models have been developed for indoor localization based on radio-frequency identification (RFID) tags. However, they often require adaptation to ensure accur…
Islanding Detection for Active Distribution Networks Using WaveNet+UNet Classifier
Amirhosein Alizadeh, Seyed Fariborz Zarei, Mohammadhadi Shateri
This paper proposes an AI-based scheme for islanding detection in active distribution networks. By reviewing existing studies, it is clear that there are several gaps in the field…
Preserving Privacy in GANs Against Membership Inference Attack
Mohammadhadi Shateri, Francisco Messina, Fabrice Labeau +1
Generative Adversarial Networks (GANs) have been widely used for generating synthetic data for cases where there is a limited size real-world dataset or when data holders are unwil…
-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing
MirHamed Jafarzadeh Asl, Mohammadhadi Shateri, Fabrice Labeau
This paper adopts Arimoto's -Mutual Information as a tunable privacy measure, in a privacy-preserving data release setting that aims to prevent disclosing private data to advers…
Cardiotocography Signal Abnormality Detection based on Deep Unsupervised Models
Julien Bertieaux, Mohammadhadi Shateri, Fabrice Labeau +1
Cardiotocography (CTG) is a key element when it comes to monitoring fetal well-being. Obstetricians use it to observe the fetal heart rate (FHR) and the uterine contraction (UC). T…
Learning Sparse Privacy-Preserving Representations for Smart Meters Data
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1
Fine-grained Smart Meters (SMs) data recording and communication has enabled several features of Smart Grids (SGs) such as power quality monitoring, load forecasting, fault detecti…
Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1
The explosion of data collection has raised serious privacy concerns in users due to the possibility that sharing data may also reveal sensitive information. The main goal of a pri…
On the Impact of Side Information on Smart Meter Privacy-Preserving Methods
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1
Smart meters (SMs) can pose privacy threats for consumers, an issue that has received significant attention in recent years. This paper studies the impact of Side Information (SI)…
Privacy-Cost Management in Smart Meters with Mutual Information-Based Reinforcement Learning
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1
The rapid development and expansion of the Internet of Things (IoT) paradigm has drastically increased the collection and exchange of data between sensors and systems, a phenomenon…
Privacy-Preserving Adversarial Network (PPAN) for Continuous non-Gaussian Attributes
Mohammadhadi Shateri, Fabrice Labeau
A privacy-preserving adversarial network (PPAN) was recently proposed as an information-theoretical framework to address the issue of privacy in data sharing. The main idea of this…
Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1
Smart meters (SMs) play a pivotal rule in the smart grid by being able to report the electricity usage of consumers to the utility provider (UP) almost in real-time. However, this…
Real-Time Privacy-Preserving Data Release for Smart Meters
Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1
Smart Meters (SMs) are able to share the power consumption of users with utility providers almost in real-time. These fine-grained signals carry sensitive information about users,…