Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Kashyap Chitta"'
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 23:14741-14752
Deep Neural Networks (DNNs) often rely on very large datasets for training. Given the large size of such datasets, it is conceivable that they contain certain samples that either do not contribute or negatively impact the DNN's optimization. Modifyin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b6944ae54d5ebfe0dbb0b8f6358d255
https://doi.org/10.1109/tits.2021.3133268
https://doi.org/10.1109/tits.2021.3133268
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198380
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77899ab8b12bdad81787a90252b826e5
https://doi.org/10.1007/978-3-031-19839-7_20
https://doi.org/10.1007/978-3-031-19839-7_20
Publikováno v:
CVPR
How should representations from complementary sensors be integrated for autonomous driving? Geometry-based sensor fusion has shown great promise for perception tasks such as object detection and motion forecasting. However, for the actual driving tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a7f2d30e25c728d71304da224c2203a
Publikováno v:
CVPR
Human drivers have a remarkable ability to drive in diverse visual conditions and situations, e.g., from maneuvering in rainy, limited visibility conditions with no lane markings to turning in a busy intersection while yielding to pedestrians. In con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21a0cd8e9272c91904f53a8ad7aedcda
https://doi.org/10.1109/cvpr42600.2020.01131
https://doi.org/10.1109/cvpr42600.2020.01131
Publikováno v:
CVPR
Data aggregation techniques can significantly improve vision-based policy learning within a training environment, e.g., learning to drive in a specific simulation condition. However, as on-policy data is sequentially sampled and added in an iterative
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74257e7cca14f09c44935f234ce8ba25
https://doi.org/10.1109/cvpr42600.2020.01178
https://doi.org/10.1109/cvpr42600.2020.01178
Publikováno v:
IROS
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8585791679e83618440fae464709043e
http://arxiv.org/abs/2005.10091
http://arxiv.org/abs/2005.10091
Publikováno v:
WACV
2020 IEEE Winter Conference on Applications of Computer Vision (WACV 2020)
2020 IEEE Winter Conference on Applications of Computer Vision (WACV 2020)
Semantic segmentation with Convolutional Neural Networks is a memory-intensive task due to the high spatial resolution of feature maps and output predictions. In this paper, we present Quadtree Generating Networks (QGNs), a novel approach able to dra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd0b5fce292af947af0da97fce8adb54
http://arxiv.org/abs/1907.11821
http://arxiv.org/abs/1907.11821
Autor:
Kashyap Chitta
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110178
ECCV Workshops (4)
ECCV Workshops (4)
We propose Attentive Regularization (AR), a method to constrain the activation maps of kernels in Convolutional Neural Networks (CNNs) to specific regions of interest (ROIs). Each kernel learns a location of specialization along with its weights thro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a4761f8f50ca6568a45c43b256ca981
https://doi.org/10.1007/978-3-030-11018-5_34
https://doi.org/10.1007/978-3-030-11018-5_34
Publikováno v:
ACM Transactions on Architecture & Code Optimization; Dec2024, Vol. 21 Issue 4, p1-20, 20p
Publikováno v:
ACM Transactions on Intelligent Systems & Technology; Jun2024, Vol. 15 Issue 3, p1-26, 26p