Robustness

Making vision and vision-language models robust to noise, occlusion, adversarial attacks, and distribution shift.

(Schiappa et al., 2023) (Schiappa et al., 2022) (Schiappa et al., 2024) (Jain et al., 2023) (Ambati et al., 2023) (Pathak et al., 2026) (Rizve et al., 2021)

References

2026

Robust Onion: Peeling Open Vocab Object Detectors Under Noise

Priyank Pathak, M. Karuppasamy, A. Baranwal, Shruti Vyas, and Yogesh S. Rawat

In European Conference on Computer Vision (ECCV), 2026

ECCV arXiv Bib Code Website

@inproceedings{pathak2026onion,
  title = {Robust Onion: Peeling Open Vocab Object Detectors Under Noise},
  author = {Pathak, Priyank and Karuppasamy, M. and Baranwal, A. and Vyas, Shruti and Rawat, Yogesh S.},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
}

2024

Robustness analysis on foundational segmentation models

Madeline Chantry Schiappa, Shehreen Azad, Sachidanand Vs, Yunhao Ge, Ondrej Miksik, Yogesh S Rawat, and Vibhav Vineet

In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024

CVPRW Bib

@inproceedings{schiappa2024robustness,
  title = {Robustness analysis on foundational segmentation models},
  author = {Schiappa, Madeline Chantry and Azad, Shehreen and Vs, Sachidanand and Ge, Yunhao and Miksik, Ondrej and Rawat, Yogesh S and Vineet, Vibhav},
  booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  pages = {1786--1796},
  year = {2024},
}

2023

A large-scale robustness analysis of video action recognition models

Madeline Chantry Schiappa, Naman Biyani, Prudvi Kamtam, Shruti Vyas, Hamid Palangi, Vibhav Vineet, and Yogesh S Rawat

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

CVPR Bib Code

@inproceedings{schiappa2023large,
  title = {A large-scale robustness analysis of video action recognition models},
  author = {Schiappa, Madeline Chantry and Biyani, Naman and Kamtam, Prudvi and Vyas, Shruti and Palangi, Hamid and Vineet, Vibhav and Rawat, Yogesh S},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {14698--14708},
  year = {2023},
}

Efficiently robustify pre-trained models

Nishant Jain, Harkirat Behl, Yogesh Singh Rawat, and Vibhav Vineet

In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Bib

@inproceedings{jain2023efficiently,
  title = {Efficiently robustify pre-trained models},
  author = {Jain, Nishant and Behl, Harkirat and Rawat, Yogesh Singh and Vineet, Vibhav},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {5505--5515},
  year = {2023},
}

PRAT: PRofiling Adversarial aTtacks

Rahul Ambati, Naveed Akhtar, Ajmal Mian, and Yogesh S Rawat

In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Bib

@inproceedings{ambati2023prat,
  title = {PRAT: PRofiling Adversarial aTtacks},
  author = {Ambati, Rahul and Akhtar, Naveed and Mian, Ajmal and Rawat, Yogesh S},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {3667--3676},
  year = {2023},
}

2022

Robustness analysis of video-language models against visual and language perturbations

Madeline Schiappa, Shruti Vyas, Hamid Palangi, Yogesh Rawat, and Vibhav Vineet

Advances in Neural Information Processing Systems, 2022

NeurIPS Bib PDF Website

@article{schiappa2022robustness,
  title = {Robustness analysis of video-language models against visual and language perturbations},
  author = {Schiappa, Madeline and Vyas, Shruti and Palangi, Hamid and Rawat, Yogesh and Vineet, Vibhav},
  journal = {Advances in Neural Information Processing Systems},
  volume = {35},
  pages = {34405--34420},
  year = {2022},
}

2021

In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning

Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, and Mubarak Shah

In The International Conference on Learning Representations (ICLR), 2021

ICLR Bib PDF Video Code

@inproceedings{rizve2021defense,
  title = {In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning},
  author = {Rizve, Mamshad Nayeem and Duarte, Kevin and Rawat, Yogesh S and Shah, Mubarak},
  booktitle = {The International Conference on Learning Representations (ICLR)},
  year = {2021},
}