no code implementations • 6 Nov 2024 • Saketh Bachu, Erfan Shayegani, Trishna Chakraborty, Rohit Lal, Arindam Dutta, Chengyu Song, Yue Dong, Nael Abu-Ghazaleh, Amit K. Roy-Chowdhury
Vision-language models (VLMs) have improved significantly in multi-modal tasks, but their more complex architecture makes their safety alignment more challenging than the alignment of large language models (LLMs).
no code implementations • 18 Oct 2024 • Calvin-Khang Ta, Arindam Dutta, Rohit Kundu, Rohit Lal, Hannah Dela Cruz, Dripta S. Raychaudhuri, Amit Roy-Chowdhury
However, ensuring the validity of SMPL configurations during tasks such as human mesh regression remains a significant challenge , highlighting the necessity for a robust human pose prior capable of discerning realistic human poses.
no code implementations • 30 Sep 2024 • Sujit Roy, Talwinder Singh, Marcus Freitag, Johannes Schmude, Rohit Lal, Dinesha Hegde, Soumya Ranjan, Amy Lin, Vishal Gaur, Etienne Eben Vos, Rinki Ghosal, Badri Narayana Patro, Berkay Aydin, Nikolai Pogorelov, Juan Bernabe Moreno, Manil Maskey, Rahul Ramachandran
Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications.
2 code implementations • 20 Sep 2024 • Johannes Schmude, Sujit Roy, Will Trojak, Johannes Jakubik, Daniel Salles Civitarese, Shraddha Singh, Julian Kuehnert, Kumar Ankur, Aman Gupta, Christopher E Phillips, Romeo Kienzler, Daniela Szwarcman, Vishal Gaur, Rajat Shinde, Rohit Lal, Arlindo Da Silva, Jorge Luis Guevara Diaz, Anne Jones, Simon Pfreundschuh, Amy Lin, Aditi Sheshadri, Udaysankar Nair, Valentine Anantharaj, Hendrik Hamann, Campbell Watson, Manil Maskey, Tsengdar J Lee, Juan Bernabe Moreno, Rahul Ramachandran
Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting.
no code implementations • 28 Jul 2024 • Vikash Kumar, Himanshu Patil, Rohit Lal, Anirban Chakraborty
Most of the Unsupervised Domain Adaptation (UDA) algorithms focus on reducing the global domain shift between labelled source and unlabelled target domains by matching the marginal distributions under a small domain gap assumption.
no code implementations • 4 Jul 2024 • Arindam Dutta, Rohit Lal, Yash Garg, Calvin-Khang Ta, Dripta S. Raychaudhuri, Hannah Dela Cruz, Amit K. Roy-Chowdhury
Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision.
no code implementations • 24 Dec 2023 • Rohit Lal, Saketh Bachu, Yash Garg, Arindam Dutta, Calvin-Khang Ta, Dripta S. Raychaudhuri, Hannah Dela Cruz, M. Salman Asif, Amit K. Roy-Chowdhury
This challenge arises because these models struggle to generalize beyond their training datasets, and the variety of occlusions is hard to capture in the training data.
no code implementations • 5 Dec 2023 • Rohit Kundu, Sudipta Paul, Rohit Lal, Amit K. Roy-Chowdhury
Specifically, we propose an approach to enable the Segment Anything Model (SAM) with semantic recognition capability to generate pixel-level annotations for images without any manual supervision.
1 code implementation • 9 Nov 2023 • Arindam Dutta, Rohit Lal, Dripta S. Raychaudhuri, Calvin Khang Ta, Amit K. Roy-Chowdhury
Human silhouette extraction is a fundamental task in computer vision with applications in various downstream tasks.
no code implementations • ICCV 2023 • Dripta S. Raychaudhuri, Calvin-Khang Ta, Arindam Dutta, Rohit Lal, Amit K. Roy-Chowdhury
To address this limitation, we focus on the task of source-free domain adaptation for pose estimation, where a source model must adapt to a new target domain using only unlabeled target data.
no code implementations • 2 Feb 2023 • Rohit Lal, Arihant Gaur, Aadhithya Iyer, Muhammed Abdullah Shaikh, Ritik Agrawal
Single-Source Single-Target Domain Adaptation (1S1T) aims to bridge the gap between a labelled source domain and an unlabelled target domain.
1 code implementation • 7 Nov 2022 • Vikash Kumar, Rohit Lal, Himanshu Patil, Anirban Chakraborty
The main motive of this work is to solve for Single and Multi target Domain Adaptation (SMTDA) for the source-free paradigm, which enforces a constraint where the labeled source data is not available during target adaptation due to various privacy-related restrictions on data sharing.
no code implementations • 8 Aug 2022 • Rohit Lal, Bharath Kumar Bolla, Sabeesh Ethiraj
Our work sheds light on the fact that custom networks with efficient architectures and faster inference times can be built without the need of relying on pre-trained architectures.
no code implementations • 5 May 2022 • Gaurav Kumar Nayak, Ruchit Rawal, Rohit Lal, Himanshu Patil, Anirban Chakraborty
We, therefore, propose a holistic approach for quantifying adversarial vulnerability of a sample by combining these different perspectives, i. e., degree of model's reliance on high-frequency features and the (conventional) sample-distance to the decision boundary.