Zobrazeno 1 - 10
of 93
pro vyhledávání: '"LATHUILIÈRE, STÉPHANE"'
Large-scale pre-trained audio and image models demonstrate an unprecedented degree of generalization, making them suitable for a wide range of applications. Here, we tackle the specific task of sound-prompted segmentation, aiming to segment image reg
Externí odkaz:
http://arxiv.org/abs/2412.01488
Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for audio captio
Externí odkaz:
http://arxiv.org/abs/2410.05997
Autor:
Rahman, Muhammad Rameez Ur, Giraldo, Jhony H., Spinelli, Indro, Lathuilière, Stéphane, Galasso, Fabio
Event cameras, known for low-latency operation and superior performance in challenging lighting conditions, are suitable for sensitive computer vision tasks such as semantic segmentation in autonomous driving. However, challenges arise due to limited
Externí odkaz:
http://arxiv.org/abs/2408.09424
Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose $\textit{Specify ANd Edit}$ (SANE), a zero-shot inference pipeline for diffusion-based editing systems.
Externí odkaz:
http://arxiv.org/abs/2407.20232
Re-Identification systems (Re-ID) are crucial for public safety but face the challenge of having to adapt to environments that differ from their training distribution. Furthermore, rigorous privacy protocols in public places are being enforced as app
Externí odkaz:
http://arxiv.org/abs/2407.12589
Machine unlearning (MU) aims to erase data from a model as if it never saw them during training. To this extent, existing MU approaches assume complete or partial access to the training data, which can be limited over time due to privacy regulations.
Externí odkaz:
http://arxiv.org/abs/2407.12069
Prompt tuning has emerged as an effective rehearsal-free technique for class-incremental learning (CIL) that learns a tiny set of task-specific parameters (or prompts) to instruct a pre-trained transformer to learn on a sequence of tasks. Albeit effe
Externí odkaz:
http://arxiv.org/abs/2405.15633
Online Unsupervised Domain Adaptation (OUDA) for person Re-Identification (Re-ID) is the task of continuously adapting a model trained on a well-annotated source domain dataset to a target domain observed as a data stream. In OUDA, person Re-ID model
Externí odkaz:
http://arxiv.org/abs/2402.15206
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 DGSS methods typically effectuate robust features by means of Domain Rand
Externí odkaz:
http://arxiv.org/abs/2312.09788
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 unavailable while learning on the current task data. CL is essentially a balan
Externí odkaz:
http://arxiv.org/abs/2312.08977