Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Borse, Shubhankar"'
Autor:
Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, Priyadarshi, Sweta, Ganapathy, Viswanath, Esteves, Rafael, Kadambi, Shreya, Borse, Shubhankar, Whatmough, Paul, Garrepalli, Risheek, Van Baalen, Mart, Teague, Harris, Nagel, Markus
In this paper, we propose Sparse High Rank Adapters (SHiRA) that directly finetune 1-2% of the base model weights while leaving others unchanged, thus, resulting in a highly sparse adapter. This high sparsity incurs no inference overhead, enables rap
Externí odkaz:
http://arxiv.org/abs/2407.16712
Autor:
Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, Priyadarshi, Sweta, Ganapathy, Viswanath, Esteves, Rafael, Kadambi, Shreya, Borse, Shubhankar, Whatmough, Paul, Garrepalli, Risheek, Van Baalen, Mart, Teague, Harris, Nagel, Markus
Low Rank Adaptation (LoRA) has gained massive attention in the recent generative AI research. One of the main advantages of LoRA is its ability to be fused with pretrained models adding no overhead during inference. However, from a mobile deployment
Externí odkaz:
http://arxiv.org/abs/2406.13175
Autor:
Borse, Shubhankar, Kadambi, Shreya, Pandey, Nilesh Prasad, Bhardwaj, Kartikeya, Ganapathy, Viswanath, Priyadarshi, Sweta, Garrepalli, Risheek, Esteves, Rafael, Hayat, Munawar, Porikli, Fatih
While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated images, as the model tends to copy data from the observed training samples
Externí odkaz:
http://arxiv.org/abs/2406.08798
Autor:
VS, Vibashan, Borse, Shubhankar, Park, Hyojin, Das, Debasmit, Patel, Vishal, Hayat, Munawar, Porikli, Fatih
In this paper, we introduce an open-vocabulary panoptic segmentation model that effectively unifies the strengths of the Segment Anything Model (SAM) with the vision-language CLIP model in an end-to-end framework. While SAM excels in generating spati
Externí odkaz:
http://arxiv.org/abs/2403.09620
Autor:
Unger, David, Gosala, Nikhil, Kumar, Varun Ravi, Borse, Shubhankar, Valada, Abhinav, Yogamani, Senthil
Most automated driving systems comprise a diverse sensor set, including several cameras, Radars, and LiDARs, ensuring a complete 360\deg coverage in near and far regions. Unlike Radar and LiDAR, which measure directly in 3D, cameras capture a 2D pers
Externí odkaz:
http://arxiv.org/abs/2309.09080
Autor:
Borse, Shubhankar, Yogamani, Senthil, Klingner, Marvin, Ravi, Varun, Cai, Hong, Almuzairee, Abdulaziz, Porikli, Fatih
Bird's-eye-view (BEV) grid is a typical representation of the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is fundamentally constr
Externí odkaz:
http://arxiv.org/abs/2306.03810
In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation. 4D panoptic segmentation is a benchmark task for autonomous driving that requires recognizing semantic classes and object instances on the road based on LiDA
Externí odkaz:
http://arxiv.org/abs/2303.15651
Autor:
Klingner, Marvin, Borse, Shubhankar, Kumar, Varun Ravi, Rezaei, Behnaz, Narayanan, Venkatraman, Yogamani, Senthil, Porikli, Fatih
Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of features fro
Externí odkaz:
http://arxiv.org/abs/2303.02203
Autor:
Borse, Shubhankar, Das, Debasmit, Park, Hyojin, Cai, Hong, Garrepalli, Risheek, Porikli, Fatih
We present DejaVu, a novel framework which leverages conditional image regeneration as additional supervision during training to improve deep networks for dense prediction tasks such as segmentation, depth estimation, and surface normal prediction. F
Externí odkaz:
http://arxiv.org/abs/2303.01573
Autor:
Das, Debasmit, Borse, Shubhankar, Park, Hyojin, Azarian, Kambiz, Cai, Hong, Garrepalli, Risheek, Porikli, Fatih
Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion. To tackle
Externí odkaz:
http://arxiv.org/abs/2302.14611