DNA: Dynamic Network Augmentation
Salvato in:
| Pubblicato in: | arXiv.org (Dec 17, 2021), p. n/a |
|---|---|
| Autore principale: | |
| Altri autori: | , |
| Pubblicazione: |
Cornell University Library, arXiv.org
|
| Soggetti: | |
| Accesso online: | Citation/Abstract Full text outside of ProQuest |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2611834890 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2611834890 | ||
| 045 | 0 | |b d20211217 | |
| 100 | 1 | |a Mahan, Scott | |
| 245 | 1 | |a DNA: Dynamic Network Augmentation | |
| 260 | |b Cornell University Library, arXiv.org |c Dec 17, 2021 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a In many classification problems, we want a classifier that is robust to a range of non-semantic transformations. For example, a human can identify a dog in a picture regardless of the orientation and pose in which it appears. There is substantial evidence that this kind of invariance can significantly improve the accuracy and generalization of machine learning models. A common technique to teach a model geometric invariances is to augment training data with transformed inputs. However, which invariances are desired for a given classification task is not always known. Determining an effective data augmentation policy can require domain expertise or extensive data pre-processing. Recent efforts like AutoAugment optimize over a parameterized search space of data augmentation policies to automate the augmentation process. While AutoAugment and similar methods achieve state-of-the-art classification accuracy on several common datasets, they are limited to learning one data augmentation policy. Often times different classes or features call for different geometric invariances. We introduce Dynamic Network Augmentation (DNA), which learns input-conditional augmentation policies. Augmentation parameters in our model are outputs of a neural network and are implicitly learned as the network weights are updated. Our model allows for dynamic augmentation policies and performs well on data with geometric transformations conditional on input features. | |
| 653 | |a Geometric transformation | ||
| 653 | |a Classification | ||
| 653 | |a Neural networks | ||
| 653 | |a Machine learning | ||
| 653 | |a Data search | ||
| 653 | |a Policies | ||
| 653 | |a Data augmentation | ||
| 700 | 1 | |a Doster, Tim | |
| 700 | 1 | |a Kvinge, Henry | |
| 773 | 0 | |t arXiv.org |g (Dec 17, 2021), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2611834890/abstract/embedded/75I98GEZK8WCJMPQ?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2112.09277 |