Zobrazeno 1 - 10
of 102
pro vyhledávání: '"Vijay Kumar, B."'
Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer f
Externí odkaz:
http://arxiv.org/abs/2401.00125
Autor:
Zhao, Shiyu, Zhao, Long, G, Vijay Kumar B., Suh, Yumin, Metaxas, Dimitris N., Chandraker, Manmohan, Schulter, Samuel
The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has
Externí odkaz:
http://arxiv.org/abs/2401.00094
Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are fundamentally
Externí odkaz:
http://arxiv.org/abs/2311.01295
Autor:
Zhao, Shiyu, Schulter, Samuel, Zhao, Long, Zhang, Zhixing, G, Vijay Kumar B., Suh, Yumin, Chandraker, Manmohan, Metaxas, Dimitris N.
Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm
Externí odkaz:
http://arxiv.org/abs/2308.06412
Autor:
Schulter, Samuel, G, Vijay Kumar B, Suh, Yumin, Dafnis, Konstantinos M., Zhang, Zhixing, Zhao, Shiyu, Metaxas, Dimitris
Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper evaluation is la
Externí odkaz:
http://arxiv.org/abs/2304.11463
Autor:
Zhao, Shiyu, Zhang, Zhixing, Schulter, Samuel, Zhao, Long, G, Vijay Kumar B., Stathopoulos, Anastasis, Chandraker, Manmohan, Metaxas, Dimitris
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We propose a novel
Externí odkaz:
http://arxiv.org/abs/2207.08954
Autor:
G, Vijay Kumar B, Subramanian, Jeyasri, Chordia, Varnith, Bart, Eugene, Fang, Shaobo, Guan, Kelly, Bala, Raja
We propose replacing scene text in videos using deep style transfer and learned photometric transformations.Building on recent progress on still image text replacement,we present extensions that alter text while preserving the appearance and motion c
Externí odkaz:
http://arxiv.org/abs/2109.02762
Publikováno v:
In Materials Today: Proceedings 2023 80 Part 3:1747-1750
This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires annotation mask
Externí odkaz:
http://arxiv.org/abs/1806.00911
To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples
Externí odkaz:
http://arxiv.org/abs/1704.01285