Zobrazeno 1 - 10
of 3 393
pro vyhledávání: '"Salzmann P"'
Autor:
Aharonian, F., Benkhali, F. Ait, Aschersleben, J., Ashkar, H., Backes, M., Martins, V. Barbosa, Batzofin, R., Becherini, Y., Berge, D., Bernlöhr, K., Bi, B., Böttcher, M., Boisson, C., Bolmont, J., de Lavergne, M. de Bony, Borowska, J., Bouyahiaoui, M., Brose, R., Brown, A., Brun, F., Bruno, B., Bulik, T., Burger-Scheidlin, C., Bylund, T., Casanova, S., Celic, J., Cerruti, M., Chand, T., Chandra, S., Chen, A., Chibueze, J., Chibueze, O., Collins, T., Cotter, G., Mbarubucyeye, J. Damascene, Devin, J., Djuvsland, J., Dmytriiev, A., Egberts, K., Einecke, S., Ernenwein, J. -P., Fegan, S., Feijen, K., Fontaine, G., Funk, S., Gabici, S., Gallant, Y. A., Glicenstein, J. F., Glombitza, J., Grolleron, G., Heß, B., Hofmann, W., Holch, T. L., Holler, M., Horns, D., Huang, Zhiqiu, Jamrozy, M., Jankowsky, F., Joshi, V., Jung-Richardt, I., Kasai, E., Katarzynski, K., Kerszberg, D., Khatoon, R., Khelifi, B., Kluzniak, W., Komin, Nu., Kosack, K., Kostunin, D., Kundu, A., Lang, R. G., Stum, S. Le, Leitl, F., Lemiere, A., Lemoine-Goumard, M., Lenain, J. -P., Leuschner, F., Luashvili, A., Mackey, J., Malyshev, D., Marandon, V., Marinos, P., Marti-Devesa, G., Marx, R., Meyer, M., Mitchell, A., Moderski, R., Moghadam, M. O., Mohrmann, L., Montanari, A., Moulin, E., de Naurois, M., Niemiec, J., Ohm, S., Olivera-Nieto, L., Wilhelmi, E. de Ona, Ostrowski, M., Panny, S., Panter, M., Parsons, D., Pensec, U., Peron, G., Pühlhofer, G., Punch, M., Quirrenbach, A., Ravikularaman, S., Regeard, M., Reimer, A., Reimer, O., Reis, I., Ren, H., Reville, B., Rieger, F., Rowell, G., Rudak, B., Ruiz-Velasco, E., Sahakian, V., Salzmann, H., Santangelo, A., Sasaki, M., Schäfer, J., Schüssler, F., Schutte, H. M., Shapopi, J. N. S., Sharma, A., Sol, H., Spencer, S., Stawarz, L., Steinmassl, S., Steppa, C., Suzuki, H., Takahashi, T., Tanaka, T., Taylor, A. M., Terrier, R., Tsirou, M., van Eldik, C., Vecchi, M., Venter, C., Vink, J., Wach, T., Wagner, S. J., Wierzcholska, A., Zacharias, M., Zdziarski, A. A., Zech, A., Zywucka, N.
Owing to their rapid cooling rate and hence loss-limited propagation distance, cosmic-ray electrons and positrons (CRe) at very high energies probe local cosmic-ray accelerators and provide constraints on exotic production mechanisms such as annihila
Externí odkaz:
http://arxiv.org/abs/2411.08189
In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety and generalize to new domains. However, existing methods often struggle to distinguish between domain-level
Externí odkaz:
http://arxiv.org/abs/2411.03829
3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness for novel view synthesis (NVS). However, the 3DGS model tends to overfit when trained with sparse posed views, limiting its generalization capacity for broader pose variations. In
Externí odkaz:
http://arxiv.org/abs/2411.00144
Autor:
Grönquist, Peter, Bhattacharjee, Deblina, Aydemir, Bahar, Ozaydin, Baran, Zhang, Tong, Salzmann, Mathieu, Süsstrunk, Sabine
In the evolving landscape of deep learning, there is a pressing need for more comprehensive datasets capable of training models across multiple modalities. Concurrently, in digital humanities, there is a growing demand to leverage technology for dive
Externí odkaz:
http://arxiv.org/abs/2410.20459
Domain Generalization (DG) aims to train models that perform well not only on the training (source) domains but also on novel, unseen target data distributions. A key challenge in DG is preventing overfitting to source domains, which can be mitigated
Externí odkaz:
http://arxiv.org/abs/2410.06020
Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data augmentation me
Externí odkaz:
http://arxiv.org/abs/2409.07307
Autor:
Salzmann, Robert
Frequent applications of a mixing quantum operation to a quantum system slow down its time evolution and eventually drive it into the invariant subspace of the named operation. We prove this phenomenon, the quantum Zeno effect, and its continuous var
Externí odkaz:
http://arxiv.org/abs/2409.06469
Recently, diffusion-based generative models have demonstrated remarkable performance in speech enhancement tasks. However, these methods still encounter challenges, including the lack of structural information and poor performance in low Signal-to-No
Externí odkaz:
http://arxiv.org/abs/2409.05116
Estimating the fidelity between a desired target quantum state and an actual prepared state is essential for assessing the success of experiments. For pure target states, we use functional representations that can be measured directly and determine t
Externí odkaz:
http://arxiv.org/abs/2409.04189
Autor:
Sauvalle, Bruno, Salzmann, Mathieu
We are considering in this paper the task of label-efficient fine-tuning of segmentation models: We assume that a large labeled dataset is available and allows to train an accurate segmentation model in one domain, and that we have to adapt this mode
Externí odkaz:
http://arxiv.org/abs/2408.03433