Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Griffin, Brent A."'
We introduce a new framework for analyzing classification datasets based on the ratios of reconstruction errors between autoencoders trained on individual classes. This analysis framework enables efficient characterization of datasets on the sample,
Externí odkaz:
http://arxiv.org/abs/2412.02596
Deep learning increasingly relies on massive data with substantial costs for storage, annotation, and model training. To reduce these costs, coreset selection aims to find a representative subset of data to train models while ideally performing on pa
Externí odkaz:
http://arxiv.org/abs/2411.15349
Autor:
Griffin, Brent
This paper addresses the problem of mobile robot manipulation using object detection. Our approach uses detection and control as complimentary functions that learn from real-world interactions. We develop an end-to-end manipulation method based solel
Externí odkaz:
http://arxiv.org/abs/2201.12437
Autor:
Griffin, Brent A., Corso, Jason J.
This paper addresses the problem of learning to estimate the depth of detected objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by 1) designing a recurrent neural network (DBox) that e
Externí odkaz:
http://arxiv.org/abs/2103.01468
Autor:
Griffin, Brent A., Corso, Jason J.
Video object segmentation, i.e., the separation of a target object from background in video, has made significant progress on real and challenging videos in recent years. To leverage this progress in 3D applications, this paper addresses the problem
Externí odkaz:
http://arxiv.org/abs/2007.05676
To be effective in unstructured and changing environments, robots must learn to recognize new objects. Deep learning has enabled rapid progress for object detection and segmentation in computer vision; however, this progress comes at the price of hum
Externí odkaz:
http://arxiv.org/abs/1904.00952
Autor:
Griffin, Brent A., Corso, Jason J.
Semi-supervised video object segmentation has made significant progress on real and challenging videos in recent years. The current paradigm for segmentation methods and benchmark datasets is to segment objects in video provided a single annotation i
Externí odkaz:
http://arxiv.org/abs/1903.11779
To be useful in everyday environments, robots must be able to identify and locate real-world objects. In recent years, video object segmentation has made significant progress on densely separating such objects from background in real and challenging
Externí odkaz:
http://arxiv.org/abs/1903.08336
To be useful in everyday environments, robots must be able to observe and learn about objects. Recent datasets enable progress for classifying data into known object categories; however, it is unclear how to collect reliable object data when operatin
Externí odkaz:
http://arxiv.org/abs/1901.05580
Autor:
Griffin, Brent A., Corso, Jason J.
We investigate the problem of strictly unsupervised video object segmentation, i.e., the separation of a primary object from background in video without a user-provided object mask or any training on an annotated dataset. We find foreground objects i
Externí odkaz:
http://arxiv.org/abs/1811.07958