Search Results - "Bhotika, Rahul"

Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training by Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of shots (shot-free). Rather than fixing the class…”
Get full text

Class-Incremental Learning with Strong Pre-trained Models by Wu, Tz-Ying, Swaminathan, Gurumurthy, Li, Zhizhong, Ravichandran, Avinash, Vasconcelos, Nuno, Bhotika, Rahul, Soatto, Stefano

“…Class-incremental learning (CIL) has been widely stud-ied under the setting of starting from a small number of classes (base classes). Instead, we explore an…”
Get full text

Task Adaptive Parameter Sharing for Multi-Task Learning by Wallingford, Matthew, Li, Hao, Achille, Alessandro, Ravichandran, Avinash, Fowlkes, Charless, Bhotika, Rahul, Soatto, Stefano

“…Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of…”
Get full text

End-to-end Piece-wise Unwarping of Document Images by Das, Sagnik, Singh, Kunwar Yashraj, Wu, Jon, Bas, Erhan, Mahadevan, Vijay, Bhotika, Rahul, Samaras, Dimitris

“…Document unwarping attempts to undo physical deformations of the paper and recover a 'flatbed' scanned document-image for downstream tasks such as OCR. Current…”
Get full text

Relaxing Contrastiveness in Multimodal Representation Learning by Lin, Zudi, Bas, Erhan, Singh, Kunwar Yashraj, Swaminathan, Gurumurthy, Bhotika, Rahul

“…Multimodal representation learning for images with paired raw texts can improve the usability and generality of the learned semantic concepts while…”
Get full text

Coronary artery tree tracking with robust junction detection in 3D CT Angiography by Fei Zhao, Bhotika, R

“…Computed Tomography Angiography (CTA) of the heart is a non-invasive procedure to rule out coronary artery disease or measure its extent and plan treatments…”
Get full text

Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training by Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather…”
Get full text

Semi-supervised Vision Transformers at Scale by Cai, Zhaowei, Ravichandran, Avinash, Favaro, Paolo, Wang, Manchen, Modolo, Davide, Bhotika, Rahul, Tu, Zhuowen, Soatto, Stefano

“…We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different…”
Get full text

Masked Vision and Language Modeling for Multi-modal Representation Learning by Kwon, Gukyeong, Cai, Zhaowei, Ravichandran, Avinash, Bas, Erhan, Bhotika, Rahul, Soatto, Stefano

“…In this paper, we study how to use masked signal modeling in vision and language (V+L) representation learning. Instead of developing masked language modeling…”
Get full text

Predicting Training Time Without Training by Zancato, Luca, Achille, Alessandro, Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function…”
Get full text

X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks by Cai, Zhaowei, Kwon, Gukyeong, Ravichandran, Avinash, Bas, Erhan, Tu, Zhuowen, Bhotika, Rahul, Soatto, Stefano

“…In this paper, we study the challenging instance-wise vision-language tasks, where the free-form language is required to align with the objects instead of the…”
Get full text

Class-Incremental Learning with Strong Pre-trained Models by Wu, Tz-Ying, Swaminathan, Gurumurthy, Li, Zhizhong, Ravichandran, Avinash, Vasconcelos, Nuno, Bhotika, Rahul, Soatto, Stefano

“…Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an…”
Get full text

Task Adaptive Parameter Sharing for Multi-Task Learning by Wallingford, Matthew, Li, Hao, Achille, Alessandro, Ravichandran, Avinash, Fowlkes, Charless, Bhotika, Rahul, Soatto, Stefano

“…Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of…”
Get full text

Multi-Task Incremental Learning for Object Detection by Liu, Xialei, Yang, Hao, Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge…”
Get full text

Representation Consolidation for Training Expert Students by Li, Zhizhong, Ravichandran, Avinash, Fowlkes, Charless, Polito, Marzia, Bhotika, Rahul, Soatto, Stefano

“…Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation,…”
Get full text

Physically meaningful virtual unenhanced image reconstruction from dual-energy CT by Maddah, Mahnaz, Mendonca, Paulo R S, Bhotika, Rahul

“…Virtual unenhanced (VUE) image reconstruction techniques have the potential to eliminate the need for the acquisition of a non-contrast exam in imaging…”
Get full text

Estimating informativeness of samples with Smooth Unique Information by Harutyunyan, Hrayr, Achille, Alessandro, Paolini, Giovanni, Majumder, Orchid, Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a…”
Get full text

A linearized framework and a new benchmark for model selection for fine-tuning by Deshpande, Aditya, Achille, Alessandro, Ravichandran, Avinash, Li, Hao, Zancato, Luca, Fowlkes, Charless, Bhotika, Rahul, Soatto, Stefano, Perona, Pietro

“…Fine-tuning from a collection of models pre-trained on different domains (a "model zoo") is emerging as a technique to improve test accuracy in the low-data…”
Get full text

Rethinking the Hyperparameters for Fine-tuning by Li, Hao, Chaudhari, Pratik, Yang, Hao, Lam, Michael, Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically…”
Get full text

Incremental Meta-Learning via Indirect Discriminant Alignment by Liu, Qing, Majumder, Orchid, Achille, Alessandro, Ravichandran, Avinash, Bhotika, Rahul, Soatto, Stefano

“…Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a…”
Get full text