Search Results for author: Rohit Lal

Found 14 papers, 3 papers with code

Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models

no code implementations6 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).

Safety Alignment

Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior

no code implementations18 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.

3D Human Pose Estimation Denoising

AI Foundation Model for Heliophysics: Applications, Design, and Implementation

no code implementations30 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.

Prithvi WxC: Foundation Model for Weather and Climate

2 code implementations20 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.

Improving Domain Adaptation Through Class Aware Frequency Transformation

no code implementations28 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.

Pseudo Label Unsupervised Domain Adaptation

POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation

no code implementations4 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.

Segmentation Semantic Segmentation +1

STRIDE: Single-video based Temporally Continuous Occlusion Robust 3D Pose Estimation

no code implementations24 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.

3D Human Pose Estimation 3D Pose Estimation +3

Towards Granularity-adjusted Pixel-level Semantic Annotation

no code implementations5 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.

Semantic Segmentation

Prior-guided Source-free Domain Adaptation for Human Pose Estimation

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.

2D Human Pose Estimation Pose Estimation +1

Open-Set Multi-Source Multi-Target Domain Adaptation

no code implementations2 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.

Domain Adaptation Graph Attention +1

CoNMix for Source-free Single and Multi-target Domain Adaptation

1 code implementation7 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.

Domain Adaptation Knowledge Distillation +2

Efficient Neural Net Approaches in Metal Casting Defect Detection

no code implementations8 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.

Defect Detection

Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems

no code implementations5 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.

Adversarial Attack Knowledge Distillation

Cannot find the paper you are looking for? You can Submit a new open access paper.