Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Araslanov, Nikita"'
Autor:
Meier, Johannes, Scalerandi, Luca, Dhaouadi, Oussema, Kaiser, Jacques, Araslanov, Nikita, Cremers, Daniel
Existing techniques for monocular 3D detection have a serious restriction. They tend to perform well only on a limited set of benchmarks, faring well either on ego-centric car views or on traffic camera views, but rarely on both. To encourage progres
Externí odkaz:
http://arxiv.org/abs/2408.11958
Neural implicit surfaces can be used to recover accurate 3D geometry from imperfect point clouds. In this work, we show that state-of-the-art techniques work by minimizing an approximation of a one-sided Chamfer distance. This shape metric is not sym
Externí odkaz:
http://arxiv.org/abs/2407.17058
Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global semantic categories within an image corpus without any form of annotation. Building upon recent advances in self-supe
Externí odkaz:
http://arxiv.org/abs/2404.16818
Hierarchy is a natural representation of semantic taxonomies, including the ones routinely used in image segmentation. Indeed, recent work on semantic segmentation reports improved accuracy from supervised training leveraging hierarchical label struc
Externí odkaz:
http://arxiv.org/abs/2404.03778
Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and laborious process, which limits the use of deep learning methods for classif
Externí odkaz:
http://arxiv.org/abs/2212.10368
Autor:
Bahmani, Sherwin, Hahn, Oliver, Zamfir, Eduard, Araslanov, Nikita, Cremers, Daniel, Roth, Stefan
Publikováno v:
Transactions on Machine Learning Research (TMLR) 2023
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain fixed at te
Externí odkaz:
http://arxiv.org/abs/2208.05788
We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling t
Externí odkaz:
http://arxiv.org/abs/2111.06265
Autor:
Araslanov, Nikita, Roth, Stefan
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and style transfe
Externí odkaz:
http://arxiv.org/abs/2105.00097
Autor:
Araslanov, Nikita, Roth, Stefan
Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of increased model co
Externí odkaz:
http://arxiv.org/abs/2005.08104
We identify two pathological cases of temporal inconsistencies in video generation: video freezing and video looping. To better quantify the temporal diversity, we propose a class of complementary metrics that are effective, easy to implement, data a
Externí odkaz:
http://arxiv.org/abs/1909.12400