1.7k citations · 2.2k across the 42 of their papers we have counts for
27 papers · 1 filter
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann +7
Accurately reconstructing complex full multi-object scenes from sparse observations remains a core challenge in computer vision and a key step toward scalable and reliable simulati…
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
Quentin Guimard, Federico Bartsch, Simone Caldarella +3
Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biase…
Ego: Embedding-Guided Personalization of Vision-Language Models
Soroush Seifi, Simon Gardier, Vaggelis Dorovatas +2
AI assistants that support humans in daily life are becoming increasingly feasible, driven by the rapid advancements in multimodal language models. A key challenge lies in overcomi…
Evaluating the Impact of Post-Training Quantization on Reliable VQA with Multimodal LLMs
Paul Jonas Kurz, Tobias Jan Wieczorek, Mohamed A. Abdelsalam +2
Multimodal Large Language Models (MLLM) are increasingly deployed in domains where both reliability and efficiency are critical. However, current models remain overconfident, produ…
Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
Vaggelis Dorovatas, Soroush Seifi, Gunshi Gupta +1
Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face ch…
Online In-Context Distillation for Low-Resource Vision Language Models
Zhiqi Kang, Rahaf Aljundi, Vaggelis Dorovatas +1
As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-res…
Efficient Few-Shot Continual Learning in Vision-Language Models
Aristeidis Panos, Rahaf Aljundi, Daniel Olmeda Reino +1
Vision-language models (VLMs) excel in tasks such as visual question answering and image captioning. However, VLMs are often limited by their use of pretrained image encoders, like…
Personalization Toolkit: Training Free Personalization of Large Vision Language Models
Soroush Seifi, Vaggelis Dorovatas, Matteo Cassinelli +3
Personalization of Large Vision-Language Models (LVLMs) involves customizing models to recognize specific users or object instances and to generate contextually tailored responses.…
The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
Simone Caldarella, Massimiliano Mancini, Elisa Ricci +1
Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions a…
Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
Aristeidis Panos, Rahaf Aljundi, Daniel Olmeda Reino +1
Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. Ho…
Annotation Free Semantic Segmentation with Vision Foundation Models
Soroush Seifi, Daniel Olmeda Reino, Fabien Despinoy +1
Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foun…
Incremental Object-Based Novelty Detection with Feedback Loop
Simone Caldarella, Elisa Ricci, Rahaf Aljundi
Object-based Novelty Detection (ND) aims to identify unknown objects that do not belong to classes seen during training by an object detection model. The task is particularly cruci…
Overcoming Generic Knowledge Loss with Selective Parameter Update
Wenxuan Zhang, Paul Janson, Rahaf Aljundi +1
Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies…
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino +2
In Class-Incremental Learning (CIL) an image classification system is exposed to new classes in each learning session and must be updated incrementally. Methods approaching this pr…
Calibrated Out-of-Distribution Detection with a Generic Representation
Tomas Vojir, Jan Sochman, Rahaf Aljundi +1
Out-of-distribution detection is a common issue in deploying vision models in practice and solving it is an essential building block in safety critical applications. Most of the ex…
Contrastive Classification and Representation Learning with Probabilistic Interpretation
Rahaf Aljundi, Yash Patel, Milan Sulc +2
Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness an…
A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning
Paul Janson, Wenxuan Zhang, Rahaf Aljundi +1
With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed. Some of these methods d…
Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection
Farzaneh Rezaeianaran, Rakshith Shetty, Rahaf Aljundi +3
In order to robustly deploy object detectors across a wide range of scenarios, they should be adaptable to shifts in the input distribution without the need to constantly annotate…
Continual Novelty Detection
Rahaf Aljundi, Daniel Olmeda Reino, Nikolay Chumerin +1
Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and tran…
A continual learning survey: Defying forgetting in classification tasks
Matthias De Lange, Rahaf Aljundi, Marc Masana +5
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct trai…
Exploring the Challenges towards Lifelong Fact Learning
Mohamed Elhoseiny, Francesca Babiloni, Rahaf Aljundi +3
So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the propos…
Task-Free Continual Learning
Rahaf Aljundi, Klaas Kelchtermans, Tinne Tuytelaars
Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with…
Memory Aware Synapses: Learning what (not) to forget
Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny +2
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from b…
Encoder Based Lifelong Learning
Amal Rannen Triki, Rahaf Aljundi, Mathew B. Blaschko +1
This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catas…