Mahendran, Aravindh

Understanding deep image representations by inverting them

Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval Techniques

Cited by 1,827

Scaling vision transformers to 22 billion parameters

Dehghani, M., Djolonga, J., Mustafa, B., Padlewski, P., Heek, J., Gilmer, J., Steiner, A., Caron, M., Geirhos, R., Alabdulmohsin, I., et al. (2023) · arXiv

Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Cited by 112

Object Scene Representation Transformer

Sajjadi, M. S. M., Duckworth, D., Mahendran, A., van Steenkiste, S., Pavetić, F., Lučić, M., Guibas, L. J., Greff, K., & Kipf, T. (2022) · arXiv

Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval Techniques

Cited by 29

Token Cropr: Faster ViTs for Quite a Few Tasks

Bergner, B., Lippert, C., & Mahendran, A. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Cited by 5