Zobrazeno 1 - 10
of 488
pro vyhledávání: '"Salzmann, Mathieu"'
Domain Generalization (DG) aims to train models that perform well not only on the training (source) domains but also on novel, unseen target data distributions. A key challenge in DG is preventing overfitting to source domains, which can be mitigated
Externí odkaz:
http://arxiv.org/abs/2410.06020
Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data augmentation me
Externí odkaz:
http://arxiv.org/abs/2409.07307
Recently, diffusion-based generative models have demonstrated remarkable performance in speech enhancement tasks. However, these methods still encounter challenges, including the lack of structural information and poor performance in low Signal-to-No
Externí odkaz:
http://arxiv.org/abs/2409.05116
Autor:
Sauvalle, Bruno, Salzmann, Mathieu
We are considering in this paper the task of label-efficient fine-tuning of segmentation models: We assume that a large labeled dataset is available and allows to train an accurate segmentation model in one domain, and that we have to adapt this mode
Externí odkaz:
http://arxiv.org/abs/2408.03433
Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in
Externí odkaz:
http://arxiv.org/abs/2408.02209
The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frame
Externí odkaz:
http://arxiv.org/abs/2408.02049
Vision Transformer models trained on large-scale datasets, although effective, often exhibit artifacts in the patch token they extract. While such defects can be alleviated by re-training the entire model with additional classification tokens, the un
Externí odkaz:
http://arxiv.org/abs/2407.16826
We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with either enhanced fidelity or increased diversity. Our approach involves manipulating the distribution of training and generated da
Externí odkaz:
http://arxiv.org/abs/2407.08659
Autor:
Pan, Lingzhi, Zhang, Tong, Chen, Bingyuan, Zhou, Qi, Ke, Wei, Süsstrunk, Sabine, Salzmann, Mathieu
With the advancements in denoising diffusion probabilistic models (DDPMs), image inpainting has significantly evolved from merely filling information based on nearby regions to generating content conditioned on various prompts such as text, exemplar
Externí odkaz:
http://arxiv.org/abs/2407.08019
Recent advances in deep learning such as neural radiance fields and implicit neural representations have significantly propelled the field of 3D reconstruction. However, accurately reconstructing objects with complex optical properties, such as metal
Externí odkaz:
http://arxiv.org/abs/2406.08894