Sökning: (WFRF:(Johnander Joakim)) srt2:(2023) >
You can have your e...
You can have your ensemble and run it too - Deep Ensembles Spread Over Time
-
- Meding, Isak (författare)
- Zenseact AB,Zenseact, Sweden
-
- Bodin, Alexander (författare)
- Zenseact AB,Zenseact, Sweden
-
- Tonderski, Adam (författare)
- Lund University,Lunds universitet,LTH profilområde: AI och digitalisering,LTH profilområden,Lunds Tekniska Högskola,Datorseende och maskininlärning,Forskargrupper vid Lunds universitet,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH,Computer Vision and Machine Learning,Lund University Research Groups,Zenseact AB,Zenseact, Sweden; Lund Univ, Sweden,Zenseact, Sweden; Lund University, Sweden
-
visa fler...
-
- Johnander Faxén, Joakim (författare)
- Linköping University,Linköpings universitet,Datorseende,Tekniska fakulteten,Zenseact, Sweden
-
- Petersson, Christoffer, 1979 (författare)
- Chalmers University of Technology,Chalmers tekniska högskola,Zenseact, Sweden; Chalmers Univ Technol, Sweden,Zenseact, Sweden; Chalmers University of Technology, Sweden
-
- Svensson, Lennart, 1976 (författare)
- Chalmers University of Technology,Chalmers tekniska högskola,Chalmers Univ Technol, Sweden,Chalmers University of Technology, Sweden
-
visa färre...
-
(creator_code:org_t)
- IEEE COMPUTER SOC, 2023
- 2023
- Engelska.
-
Ingår i: Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023. - : IEEE COMPUTER SOC. ; , s. 4022-4031
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://doi.org/10.1...
-
https://research.cha...
-
https://lup.lub.lu.s...
-
https://urn.kb.se/re...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Ensembles of independently trained deep neural networks yield uncertainty estimates that rival Bayesian networks in performance. They also offer sizable improvements in terms of predictive performance over single models. However, deep ensembles are not commonly used in environments with limited computational budget - such as autonomous driving - since the complexity grows linearly with the number of ensemble members. An important observation that can be made for robotics applications, such as autonomous driving, is that data is typically sequential. For instance, when an object is to be recognized, an autonomous vehicle typically observes a sequence of images, rather than a single image. This raises the question, could the deep ensemble be spread over time?In this work, we propose and analyze Deep Ensembles Spread Over Time (DESOT). The idea is to apply only a single ensemble member to each data point in the sequence, and fuse the predictions over a sequence of data points. We implement and experiment with DESOT for traffic sign classification, where sequences of tracked image patches are to be classified. We find that DESOT obtains the benefits of deep ensembles, in terms of predictive and uncertainty estimation performance, while avoiding the added computational cost. Moreover, DESOT is simple to implement and does not require sequences during training. Finally, we find that DESOT, like deep ensembles, outperform single models for out-of-distribution detection.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Systemvetenskap, informationssystem och informatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Information Systems (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- traffic sign recognition
- uncertainty estimation
- out of distribution detection
- ensemble
- ensemble
- out of distribution detection
- traffic sign recognition
- uncertainty estimation
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)