1 code implementation • 12 Oct 2023 • Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu
The proposed approach achieves state-of-the-art results on the standard Domain Generalization benchmarks in a black-box teacher setting as well as a white-box setting where the weights of the VLM are accessible.
Ranked #2 on Domain Generalization on DomainNet
1 code implementation • 10 Jun 2023 • Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu
Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks.
1 code implementation • 20 Apr 2023 • Soumalya Nandi, Sravanti Addepalli, Harsh Rangwani, R. Venkatesh Babu
We further propose a novel \textit{training noise distribution} along with a \textit{regularized training scheme} to improve the certification within both $\ell_1$ and $\ell_2$ perturbation norms simultaneously.
1 code implementation • CVPR 2023 • Samyak Jain, Sravanti Addepalli, Pawan Sahu, Priyam Dey, R. Venkatesh Babu
Generalization of neural networks is crucial for deploying them safely in the real world.
no code implementations • CVPR 2023 • Abhipsa Basu, Sravanti Addepalli, R. Venkatesh Babu
The first component considers the frequency of answers within a question type in the training data, which addresses the concern of the class-imbalance causing the language biases.
1 code implementation • 27 Oct 2022 • Sravanti Addepalli, Samyak Jain, R. Venkatesh Babu
We first explain this contrasting behavior by viewing augmentation during training as a problem of domain generalization, and further propose Diverse Augmentation-based Joint Adversarial Training (DAJAT) to use data augmentations effectively in adversarial training.
1 code implementation • 18 Oct 2022 • Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu
The presence of images that flip Oracle predictions and those that do not makes this a challenging setting for adversarial robustness.
1 code implementation • 18 Oct 2022 • Sravanti Addepalli, Kaushal Bhogale, Priyam Dey, R. Venkatesh Babu
Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches.
no code implementations • 4 Oct 2022 • Sravanti Addepalli, Anshul Nasery, R. Venkatesh Babu, Praneeth Netrapalli, Prateek Jain
To bridge the gap between these two lines of work, we first hypothesize and verify that while SB may not altogether preclude learning complex features, it amplifies simpler features over complex ones.
no code implementations • 19 Aug 2022 • Anshul Nasery, Sravanti Addepalli, Praneeth Netrapalli, Prateek Jain
We consider the problem of OOD generalization, where the goal is to train a model that performs well on test distributions that are different from the training distribution.
no code implementations • CVPR 2022 • Sunandini Sanyal, Sravanti Addepalli, R. Venkatesh Babu
In this work, we show that it is indeed possible to steal Machine Learning models by accessing only top-1 predictions (Hard Label setting) as well, without access to model gradients (Black-Box setting) or even the training dataset (Data-Free setting) within a low query budget.
1 code implementation • NeurIPS 2021 • Gaurang Sriramanan, Sravanti Addepalli, Arya Baburaj, Venkatesh Babu R
The vulnerability of Deep Neural Networks to adversarial attacks has spurred immense interest towards improving their robustness.
no code implementations • ICML Workshop AML 2021 • Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, Venkatesh Babu Radhakrishnan
The presence of images that flip Oracle predictions and those that do not, makes this a challenging setting for adversarial robustness.
1 code implementation • NeurIPS 2020 • Gaurang Sriramanan, Sravanti Addepalli, Arya Baburaj, R. Venkatesh Babu
Further, we propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses by utilizing the proposed relaxation term for both attack generation and training.
no code implementations • 31 Jul 2020 • Sravanti Addepalli, Dipesh Tamboli, R. Venkatesh Babu, Biplab Banerjee
Existing visualization methods develop high confidence images consisting of both background and foreground features.
1 code implementation • CVPR 2020 • Sravanti Addepalli, Vivek B. S., Arya Baburaj, Gaurang Sriramanan, R. Venkatesh Babu
In this work, we attempt to address this problem by training networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction.
no code implementations • 27 Dec 2019 • Sravanti Addepalli, Gaurav Kumar Nayak, Anirban Chakraborty, R. Venkatesh Babu
We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples from a trained classifier, using a novel Data-enriching GAN (DeGAN) framework.