Search Results for author: Rahul Tallamraju

Found 4 papers, 3 papers with code

Semi-Supervised Domain Adaptation by Similarity based Pseudo-label Injection

1 code implementation5 Sep 2022 Abhay Rawat, Isha Dua, Saurav Gupta, Rahul Tallamraju

In our approach, to align the two domains, we leverage contrastive losses to learn a semantically meaningful and a domain agnostic feature space using the supervised samples from both domains.

Domain Adaptation Pseudo Label +1

CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation

1 code implementation27 Aug 2022 Midhun Vayyat, Jaswin Kasi, Anuraag Bhattacharya, Shuaib Ahmed, Rahul Tallamraju

In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network.

Contrastive Learning Segmentation +3

ViTOL: Vision Transformer for Weakly Supervised Object Localization

1 code implementation14 Apr 2022 Saurav Gupta, Sourav Lakhotia, Abhay Rawat, Rahul Tallamraju

Common challenges that image classification models encounter when localizing objects are, (a) they tend to look at the most discriminative features in an image that confines the localization map to a very small region, (b) the localization maps are class agnostic, and the models highlight objects of multiple classes in the same image and, (c) the localization performance is affected by background noise.

Image Classification Object +1

AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning

no code implementations13 Jul 2020 Rahul Tallamraju, Nitin Saini, Elia Bonetto, Michael Pabst, Yu Tang Liu, Michael J. Black, Aamir Ahmad

We focus on vision-based MoCap, where the objective is to estimate the trajectory of body pose and shape of a single moving person using multiple micro aerial vehicles.

Decision Making reinforcement-learning +1

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