Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Rambour, Clément"'
Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs), e.g. CLIP, for few-shot image classification. Despite their success, most prompt learning methods trade-off between classification accuracy and robustness, e.
Externí odkaz:
http://arxiv.org/abs/2407.01400
In this work, we study the out-of-distribution (OOD) detection problem through the use of the feature space of a pre-trained deep classifier. We show that learning the density of in-distribution (ID) features with an energy-based models (EBM) leads t
Externí odkaz:
http://arxiv.org/abs/2403.10403
Autor:
Ramzi, Elias, Audebert, Nicolas, Rambour, Clément, Araujo, André, Bitot, Xavier, Thome, Nicolas
In image retrieval, standard evaluation metrics rely on score ranking, \eg average precision (AP), recall at k (R@k), normalized discounted cumulative gain (NDCG). In this work we introduce a general framework for robust and decomposable rank losses
Externí odkaz:
http://arxiv.org/abs/2309.08250
Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, such as fine-grained attribute
Externí odkaz:
http://arxiv.org/abs/2307.06795
Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, existing diffusion-based video editing approaches lack the ability to offer precise control over generated content that maintains
Externí odkaz:
http://arxiv.org/abs/2306.08707
Publikováno v:
International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA
Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid en
Externí odkaz:
http://arxiv.org/abs/2305.16966
Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have shown rec
Externí odkaz:
http://arxiv.org/abs/2212.07890
Transformer models achieve state-of-the-art results for image segmentation. However, achieving long-range attention, necessary to capture global context, with high-resolution 3D images is a fundamental challenge. This paper introduces the Full resolu
Externí odkaz:
http://arxiv.org/abs/2210.05313
State-of-the-art methods for optical flow estimation rely on deep learning, which require complex sequential training schemes to reach optimal performances on real-world data. In this work, we introduce the COMBO deep network that explicitly exploits
Externí odkaz:
http://arxiv.org/abs/2207.03790
Publikováno v:
ECCV 2022, Oct 2022, Tel-Aviv, Israel
Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity. This paper introduces a new hierarchical AP training method for pertinent i
Externí odkaz:
http://arxiv.org/abs/2207.04873