Zobrazeno 1 - 10
of 3 528
pro vyhledávání: '"P. Mundt"'
Deep networks are frequently tuned to novel tasks and continue learning from ongoing data streams. Such sequential training requires consolidation of new and past information, a challenge predominantly addressed by retaining the most important data p
Externí odkaz:
http://arxiv.org/abs/2410.05800
Medical image distributions shift constantly due to changes in patient population and discrepancies in image acquisition. These distribution changes result in performance deterioration; deterioration that continual learning aims to alleviate. However
Externí odkaz:
http://arxiv.org/abs/2407.21216
Evidence-based practice (EBP) in software engineering aims to improve decision-making in software development by complementing practitioners' professional judgment with high-quality evidence from research. We believe the use of EBP techniques may be
Externí odkaz:
http://arxiv.org/abs/2403.16827
Autor:
Busch, Florian Peter, Kamath, Roshni, Mitchell, Rupert, Stammer, Wolfgang, Kersting, Kristian, Mundt, Martin
A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting where confounders may vary in time across tasks, the challenge of mitig
Externí odkaz:
http://arxiv.org/abs/2402.06434
The quest to improve scalar performance numbers on predetermined benchmarks seems to be deeply engraved in deep learning. However, the real world is seldom carefully curated and applications are seldom limited to excelling on test sets. A practical s
Externí odkaz:
http://arxiv.org/abs/2402.04814
Autor:
Verwimp, Eli, Aljundi, Rahaf, Ben-David, Shai, Bethge, Matthias, Cossu, Andrea, Gepperth, Alexander, Hayes, Tyler L., Hüllermeier, Eyke, Kanan, Christopher, Kudithipudi, Dhireesha, Lampert, Christoph H., Mundt, Martin, Pascanu, Razvan, Popescu, Adrian, Tolias, Andreas S., van de Weijer, Joost, Liu, Bing, Lomonaco, Vincenzo, Tuytelaars, Tinne, van de Ven, Gido M.
Publikováno v:
Transactions on Machine Learning Research (TMLR), 2024
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past. In this work, we take a step back, and ask
Externí odkaz:
http://arxiv.org/abs/2311.11908
Autor:
McInnes, Lois Curfman, Heroux, Michael, Bernholdt, David E., Dubey, Anshu, Gonsiorowski, Elsa, Gupta, Rinku, Marques, Osni, Moulton, J. David, Nam, Hai Ah, Norris, Boyana, Raybourn, Elaine M., Willenbring, Jim, Almgren, Ann, Bartlett, Ross, Cranfill, Kita, Fickas, Stephen, Frederick, Don, Godoy, William, Grubel, Patricia, Hartman-Baker, Rebecca, Huebl, Axel, Lynch, Rose, Thakur, Addi Malviya, Milewicz, Reed, Miller, Mark C., Mundt, Miranda, Palmer, Erik, Parete-Koon, Suzanne, Phinney, Megan, Riley, Katherine, Rogers, David M., Sims, Ben, Stevens, Deborah, Watson, Gregory R.
Computational and data-enabled science and engineering are revolutionizing advances throughout science and society, at all scales of computing. For example, teams in the U.S. DOE Exascale Computing Project have been tackling new frontiers in modeling
Externí odkaz:
http://arxiv.org/abs/2311.02010
Identification of cracks is essential to assess the structural integrity of concrete infrastructure. However, robust crack segmentation remains a challenging task for computer vision systems due to the diverse appearance of concrete surfaces, variabl
Externí odkaz:
http://arxiv.org/abs/2309.09637
Autor:
Biswas, Arijit, Mundt, Harald
Video Multimethod Assessment Fusion (VMAF) [1], [2], [3] is a popular tool in the industry for measuring coded video quality. In this study, we propose an auditory-inspired frontend in existing VMAF for creating videos of reference and coded spectrog
Externí odkaz:
http://arxiv.org/abs/2308.03437
The results of training a neural network are heavily dependent on the architecture chosen; and even a modification of only its size, however small, typically involves restarting the training process. In contrast to this, we begin training with a smal
Externí odkaz:
http://arxiv.org/abs/2307.04526