145 citations · 224 across the 24 of their papers we have counts for
34 papers
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
Thomas De Min, Subhankar Roy, Stéphane Lathuilière +2
Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can…
DiO: Distilling Masked Diffusion Models into One-step Generator
Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière +1
Masked Diffusion Models (MDMs) have emerged as a powerful generative modeling technique. Despite their remarkable results, they typically suffer from slow inference with several st…
Group-robust Machine Unlearning
Thomas De Min, Subhankar Roy, Stéphane Lathuilière +2
Machine unlearning is an emerging paradigm to remove the influence of specific training data (i.e., the forget set) from a model while preserving its knowledge of the rest of the d…
Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering
Imad Eddine Marouf, Enzo Tartaglione, Stephane Lathuiliere +1
Continual Learning in Visual Question Answering (VQACL) requires models to acquire new visual-linguistic skills (plasticity) while preserving previously learned knowledge (stabilit…
Unlearning Personal Data from a Single Image
Thomas De Min, Massimiliano Mancini, Stéphane Lathuilière +2
Machine unlearning aims to erase data from a model as if the latter never saw them during training. While existing approaches unlearn information from complete or partial access to…
Collaborating Foundation Models for Domain Generalized Semantic Segmentation
Yasser Benigmim, Subhankar Roy, Slim Essid +2
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGS…
Weighted Ensemble Models Are Strong Continual Learners
Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione +1
In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavaila…
Mini but Mighty: Finetuning ViTs with Mini Adapters
Imad Eddine Marouf, Enzo Tartaglione, Stéphane Lathuilière
Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning. Recent wo…
Enhancing Plasticity for First Session Adaptation Continual Learning
Imad Eddine Marouf, Subhankar Roy, Stéphane Lathuilière +1
The integration of large pre-trained models (PTMs) into Class-Incremental Learning (CIL) has facilitated the development of computationally efficient strategies such as First-Sessi…
The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
Giacomo Zara, Alessandro Conti, Subhankar Roy +3
Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target datas…
Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation
Tianyu Li, Subhankar Roy, Huayi Zhou +2
To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous…
One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models
Yasser Benigmim, Subhankar Roy, Slim Essid +2
Adapting a segmentation model from a labeled source domain to a target domain, where a single unlabeled datum is available, is one the most challenging problems in domain adaptatio…
Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models
Willi Menapace, Aliaksandr Siarohin, Stéphane Lathuilière +4
Neural video game simulators emerged as powerful tools to generate and edit videos. Their idea is to represent games as the evolution of an environment's state driven by the action…
Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation
Yangsong Zhang, Subhankar Roy, Hongtao Lu +2
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unann…
GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
Cristiano Saltori, Evgeny Krivosheev, Stéphane Lathuilière +5
3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when…
Playable Environments: Video Manipulation in Space and Time
Willi Menapace, Stéphane Lathuilière, Aliaksandr Siarohin +4
We present Playable Environments - a new representation for interactive video generation and manipulation in space and time. With a single image at inference time, our novel framew…
A Unified Objective for Novel Class Discovery
Enrico Fini, Enver Sangineto, Stéphane Lathuilière +3
In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labele…
Click to Move: Controlling Video Generation with Sparse Motion
Pierfrancesco Ardino, Marco De Nadai, Bruno Lepri +2
This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying sim…
Playable Video Generation
Willi Menapace, Stéphane Lathuilière, Sergey Tulyakov +2
This paper introduces the unsupervised learning problem of playable video generation (PVG). In PVG, we aim at allowing a user to control the generated video by selecting a discrete…
Multi-Domain Image-to-Image Translation with Adaptive Inference Graph
The-Phuc Nguyen, Stéphane Lathuilière, Elisa Ricci
In this work, we address the problem of multi-domain image-to-image translation with particular attention paid to computational cost. In particular, current state of the art models…
SF-UDA: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection
Cristiano Saltori, Stéphane Lathuiliére, Nicu Sebe +2
3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due…
Learning to Cluster under Domain Shift
Willi Menapace, Stéphane Lathuilière, Elisa Ricci
While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labe…
Online Continual Learning under Extreme Memory Constraints
Enrico Fini, Stéphane Lathuilière, Enver Sangineto +2
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In t…
Motion-supervised Co-Part Segmentation
Aliaksandr Siarohin, Subhankar Roy, Stéphane Lathuilière +3
Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we p…