Spremljaj
Shahed Masoudian
Shahed Masoudian
Preverjeni e-poštni naslov na jku.at
Naslov
Navedeno
Navedeno
Leto
CP-JKU submission to dcase22: Distilling knowledge for low-complexity convolutional neural networks from a patchout audio transformer
F Schmid, S Masoudian, K Koutini, G Widmer
Tech. Rep., Detection and Classification of Acoustic Scenes and Events …, 2022
342022
Cp-jku submission to dcase23: Efficient acoustic scene classification with cp-mobile
F Schmid, T Morocutti, S Masoudian, K Koutini, G Widmer
Tech. Rep., DCASE2023 Chal-lenge, Tech. Rep, 2023
222023
Knowledge Distillation from Transformers for Low-Complexity Acoustic Scene Classification.
F Schmid, S Masoudian, K Koutini, G Widmer
DCASE, 2022
212022
Modular and on-demand bias mitigation with attribute-removal subnetworks
L Hauzenberger, S Masoudian, D Kumar, M Schedl, N Rekabsaz
arXiv preprint arXiv:2205.15171, 2022
182022
Distilling the knowledge of transformers and CNNs with CP-mobile
F Schmid, T Morocutti, S Masoudian, K Koutini, G Widmer
Proceedings of the Detection and Classification of Acoustic Scenes and …, 2023
132023
Learning general audio representations with large-scale training of patchout audio transformers
K Koutini, S Masoudian, F Schmid, H Eghbal-zadeh, J Schlüter, G Widmer
HEAR: Holistic Evaluation of Audio Representations, 65-89, 2022
72022
Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters
S Masoudian, C Volaucnik, M Schedl, N Rekabsaz
arXiv preprint arXiv:2401.16457, 2024
62024
Effective controllable bias mitigation for classification and retrieval using gate adapters (2024)
S Masoudian, C Volaucnik, M Schedl, S Masoudian
CoRR, abs/2401.16457, 0
5
Modular Debiasing of Latent User Representations in Prototype-Based Recommender Systems
AB Melchiorre, S Masoudian, D Kumar, M Schedl
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2024
22024
Simulation-assisted training of neural networks for condition monitoring of electrical drives: Approach and proof of concept
E Marth, P Zorn, F Schmid, S Masoudian, K Koutini, W Amrhein
IKMT 2022; 13. GMM/ETG-Symposium, 1-7, 2022
22022
ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale
M Frohmann, C Holtermann, S Masoudian, A Lauscher, N Rekabsaz
arXiv preprint arXiv:2310.01217, 2023
12023
Simulation-assisted Training of Neural Networks for Condition Monitoring of Electrical Drives: Enhanced Domain Adaptation Methods
F Schmid, S Masoudian, E Marth, P Zorn, K Koutini, G Widmer
IKMT 2022; 13. GMM/ETG-Symposium, 1-7, 2022
12022
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
S Masoudian, M Frohmann, N Rekabsaz, M Schedl
arXiv preprint arXiv:2409.19541, 2024
2024
The Importance of Cognitive Biases in the Recommendation Ecosystem: Evidence of Feature-Positive Effect, Ikea Effect, and Cultural Homophily
M Schedl, O Lesota, S Masoudian
2024
Domain Information Control at Inference Time for Acoustic Scene Classification
S Masoudian, K Koutini, M Schedl, G Widmer, N Rekabsaz
2023 31st European Signal Processing Conference (EUSIPCO), 181-185, 2023
2023
From simulation to real world: a domain adaptation study/submitted by Shahed Masoudian
S Masoudian
2022
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–16