Bahram Zonooz
Bahram Zonooz has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Elahe Arani
Eindhoven University of Technology
2 shared publications - Arnav Varma
Advanced Research Lab, NavInfo Europe
1 shared publication - Deepan Chakravarthi Padmanabhan
Bonn-Rhein-Sieg University of Applied Sciences
1 shared publication Elahe Arani
1 shared publication- Hemang Chawla
Advanced Research Lab, NavInfo Europe
1 shared publication - Ibrahim Batuhan Akkaya
Aselsan Research Center, Yenimahalle, Ankara, Turkey
1 shared publication
Latest Publications
- 21 April 2024
- Published by Elsevier in Pattern Recognition
- Vol. 153
Enhancing performance of vision transformers on small datasets through local inductive bias incorporation
- 21 April 2024
- Published by Elsevier in Pattern Recognition
- Vol. 153
Enhancing performance of vision transformers on small datasets through local inductive bias incorporation
- 18 October 2023
- Published by Springer Nature
- p. 281-303
Transformers in Unsupervised Structure-from-Motion
- 18 October 2023
- Published by Springer Nature
- p. 281-303
Transformers in Unsupervised Structure-from-Motion
- Open Access
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4971-4980
LSFSL: Leveraging Shape Information in Few-shot Learning
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limiteddata scenario, the challenges associated with deep neural networks, such as shortcut learning and texture bias behaviors, are further exacerbated. Moreover, the significance of addressing shortcut learning is not yet fully explored in the few-shot setup. To address these issues, we propose LSFSL, which enforces the model to learn more generalizable features utilizing the implicit prior information present in the data. Through comprehensive analyses, we demonstrate that LSFSL-trained models are less vulnerable to alteration in color schemes, statistical correlations, and adversarial perturbations leveraging the global semantics in the data. Our findings highlight the potential of incorporating relevant priors in few-shot approaches to increase robustness and generalization.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4971-4980
Open AccessLSFSL: Leveraging Shape Information in Few-shot Learning
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limiteddata scenario, the challenges associated with deep neural networks, such as shortcut learning and texture bias behaviors, are further exacerbated. Moreover, the significance of addressing shortcut learning is not yet fully explored in the few-shot setup. To address these issues, we propose LSFSL, which enforces the model to learn more generalizable features utilizing the implicit prior information present in the data. Through comprehensive analyses, we demonstrate that LSFSL-trained models are less vulnerable to alteration in color schemes, statistical correlations, and adversarial perturbations leveraging the global semantics in the data. Our findings highlight the potential of incorporating relevant priors in few-shot approaches to increase robustness and generalization.