Neural architecture search for dense prediction tasks in computer vision
Abstract: The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims at automatically designing neural network architectures in a data-driven manner rather than manually, has evolved as a popular field of research. With the advent of weight sharing strategies across architectures, NAS has become applicable to a much wider range of problems. In particular, there are now many publications for dense prediction tasks in computer vision that require pixel-level predictions, such as semantic segmentation or object detection. These tasks come with novel challenges, such as higher memory footprints due to high-resolution data, learning multi-scale representations, longer training times, and more complex and larger neural architectures. In this manuscript, we provide an overview of NAS for dense prediction tasks by elaborating on these novel challenges and surveying ways to address them to ease future research and application of existing methods to novel problems
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Anmerkungen
-
International journal of computer vision. - 131, 7 (2023) , 1784-1807, ISSN: 1573-1405
- Ereignis
-
Veröffentlichung
- (wo)
-
Freiburg
- (wer)
-
Universität
- (wann)
-
2023
- Urheber
-
Mohan, Rohit
Elsken, Thomas
Zela, Arbër
Metzen, Jan Hendrik
Staffler, Benedikt
Brox, Thomas
Valada, Abhinav
Hutter, Frank
- DOI
-
10.1007/s11263-023-01785-y
- URN
-
urn:nbn:de:bsz:25-freidok-2358457
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
25.03.2025, 13:46 MEZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Mohan, Rohit
- Elsken, Thomas
- Zela, Arbër
- Metzen, Jan Hendrik
- Staffler, Benedikt
- Brox, Thomas
- Valada, Abhinav
- Hutter, Frank
- Universität
Entstanden
- 2023
Ähnliche Objekte (12)
Evolutionary neural architecture search for the task of road traffic prediction.
Neural correlates of error prediction in a complex motor task
Neural correlates of error prediction in a complex motor task
Topology Learning for Prediction, Generation, and Robustness in Neural Architecture Search
Performance modeling and prediction for dense linear algebra
Supporting Complex Search Tasks
Causation, prediction, and search
Dense periodic packings in the light of crystal structure prediction
Neural system prediction and identification challenge
Person Movement Prediction Using Neural Networks
Neural networks for video intra prediction
Dense Rewards and Continual Reinforcement Learning for Task-oriented Dialogue Policies
Evolutionary neural architecture search for the task of road traffic prediction.
Neural correlates of error prediction in a complex motor task
Neural correlates of error prediction in a complex motor task
Topology Learning for Prediction, Generation, and Robustness in Neural Architecture Search
Performance modeling and prediction for dense linear algebra
Supporting Complex Search Tasks
Causation, prediction, and search
Dense periodic packings in the light of crystal structure prediction
Neural system prediction and identification challenge
Person Movement Prediction Using Neural Networks
Neural networks for video intra prediction
Dense Rewards and Continual Reinforcement Learning for Task-oriented Dialogue Policies
Evolutionary neural architecture search for the task of road traffic prediction.
Neural correlates of error prediction in a complex motor task
Neural correlates of error prediction in a complex motor task
Topology Learning for Prediction, Generation, and Robustness in Neural Architecture Search
Performance modeling and prediction for dense linear algebra
Supporting Complex Search Tasks
Causation, prediction, and search
Dense periodic packings in the light of crystal structure prediction
Neural system prediction and identification challenge
Person Movement Prediction Using Neural Networks
Neural networks for video intra prediction