no code implementations • ICLR 2019 • Hariharan Ravishankar, Rahul Venkataramani, Saihareesh Anamandra, Prasad Sudhakar
Despite the recent advances in representation learning, lifelong learning continues to be one of the most challenging and unconquered problems.
no code implementations • 26 Oct 2023 • Rachana Sathish, Rahul Venkataramani, K S Shriram, Prasad Sudhakar
In this work, we propose a plug-and-play Prompt Optimization Technique for foundation models like SAM (SAMPOT) that utilizes the downstream segmentation task to optimize the human-provided prompt to obtain improved performance.
no code implementations • 20 Apr 2017 • Hariharan Ravishankar, Prasad Sudhakar, Rahul Venkataramani, Sheshadri Thiruvenkadam, Pavan Annangi, Narayanan Babu, Vivek Vaidya
In this paper, we systematically investigate the process of transferring a Convolutional Neural Network, trained on ImageNet images to perform image classification, to kidney detection problem in ultrasound images.
no code implementations • 8 Dec 2016 • Rahul Venkataramani, Sheshadri Thiruvenkadam, Prasad Sudhakar, Hariharan Ravishankar, Vivek Vaidya
Typical convolutional neural networks (CNNs) have several millions of parameters and require a large amount of annotated data to train them.
no code implementations • 25 Jun 2014 • Prasad Sudhakar, Laurent Jacques, Xavier Dubois, Philippe Antoine, Luc Joannes
This compressive characterization is then confirmed with experimental results on simple plano-convex and multifocal intra-ocular lenses studying the evolution of the main deflection as a function of the object point location.