Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Scott, Tyler R."'
Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods -- including $k$-means and hierarchical agglomerative clustering -- underperform supervised, deep, inductive methods. While the reported impro
Externí odkaz:
http://arxiv.org/abs/2211.05183
Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically uniform di
Externí odkaz:
http://arxiv.org/abs/2109.05675
Recent work has argued that classification losses utilizing softmax cross-entropy are superior not only for fixed-set classification tasks, but also by outperforming losses developed specifically for open-set tasks including few-shot learning and ret
Externí odkaz:
http://arxiv.org/abs/2103.15718
Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking methods, but is often unrealist
Externí odkaz:
http://arxiv.org/abs/2006.11393
Geomorphological Analysis Using Unpiloted Aircraft Systems, Structure from Motion, and Deep Learning
Autor:
Chen, Zhiang, Scott, Tyler R., Bearman, Sarah, Anand, Harish, Keating, Devin, Scott, Chelsea, Arrowsmith, J Ramon, Das, Jnaneshwar
Publikováno v:
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
We present a pipeline for geomorphological analysis that uses structure from motion (SfM) and deep learning on close-range aerial imagery to estimate spatial distributions of rock traits (size, roundness, and orientation) along a tectonic fault scarp
Externí odkaz:
http://arxiv.org/abs/1909.12874
Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far apart. We propose a probabilistic method that treats embeddings as rando
Externí odkaz:
http://arxiv.org/abs/1909.11702
The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as inductive trans
Externí odkaz:
http://arxiv.org/abs/1805.08402
Autor:
Mayo, David, Scott, Tyler R, Ren, Mengye, Elsayed, Gamaledin, Hermann, Katherine, Jones, Matt, Mozer, Michael
Publikováno v:
Proceedings of the Annual Meeting of the Cognitive Science Society, vol 45, iss 45
The most common settings in machine learning to study multitask learning assume either that a random task is selected on each training trial, or that one task is trained to mastery and then training advances to the next. We study an intermediate sett
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______325::99fc937abcfcd6e87aa3e0080b15e12d
https://escholarship.org/uc/item/3tb956hb
https://escholarship.org/uc/item/3tb956hb