Zobrazeno 1 - 10
of 123
pro vyhledávání: '"Kanakis, Menelaos"'
Local image feature descriptors have had a tremendous impact on the development and application of computer vision methods. It is therefore unsurprising that significant efforts are being made for learning-based image point descriptors. However, the
Externí odkaz:
http://arxiv.org/abs/2312.15471
Autor:
Pataki, Zador, Altillawi, Mohammad, Kanakis, Menelaos, Pautrat, Rémi, Shen, Fengyi, Liu, Ziyuan, Van Gool, Luc, Pollefeys, Marc
Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variations, such as different seasonal
Externí odkaz:
http://arxiv.org/abs/2311.03345
Diffusion-based text-to-image models ignited immense attention from the vision community, artists, and content creators. Broad adoption of these models is due to significant improvement in the quality of generations and efficient conditioning on vari
Externí odkaz:
http://arxiv.org/abs/2309.08523
Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. However, the current practice requires additional labeling efforts for the auxiliary task, while not guaranteeing better model
Externí odkaz:
http://arxiv.org/abs/2210.07239
Efficient detection and description of geometric regions in images is a prerequisite in visual systems for localization and mapping. Such systems still rely on traditional hand-crafted methods for efficient generation of lightweight descriptors, a co
Externí odkaz:
http://arxiv.org/abs/2203.03610
The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such as transfor
Externí odkaz:
http://arxiv.org/abs/2112.09686
Autor:
Saha, Suman, Obukhov, Anton, Paudel, Danda Pani, Kanakis, Menelaos, Chen, Yuhua, Georgoulis, Stamatios, Van Gool, Luc
We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a multi-task l
Externí odkaz:
http://arxiv.org/abs/2105.07830
The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a multi-task
Externí odkaz:
http://arxiv.org/abs/2104.13874
The multi-modal nature of many vision problems calls for neural network architectures that can perform multiple tasks concurrently. Typically, such architectures have been handcrafted in the literature. However, given the size and complexity of the p
Externí odkaz:
http://arxiv.org/abs/2008.10292
Autor:
Kanakis, Menelaos, Bruggemann, David, Saha, Suman, Georgoulis, Stamatios, Obukhov, Anton, Van Gool, Luc
Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-task models are often overlooked in literature. First, enabling the mode
Externí odkaz:
http://arxiv.org/abs/2007.12540