5 papers
Chaos-Enhanced Prototypical Networks for Few-Shot Medical Image Classification
Chinthakuntla Meghan Sai, Murarisetty V Sai Kartheek, Sita Devi Bharatula +1
The scarcity of labeled clinical data in oncology makes Few-Shot Learning (FSL) a critical framework for Computer Aided Diagnostics, but we observed that standard Prototypical Netw…
BBoxCut: A Targeted Data Augmentation Technique for Enhancing Wheat Head Detection Under Occlusions
Yasashwini Sai Gowri P, Karthik Seemakurthy, Andrews Agyemang Opoku +1
Wheat plays a critical role in global food security, making it one of the most extensively studied crops. Accurate identification and measurement of key characteristics of wheat he…
Domain penalisation for improved Out-of-Distribution Generalisation
Shuvam Jena, Sushmetha Sumathi Rajendran, Karthik Seemakurthy +3
In the field of object detection, domain generalisation (DG) aims to ensure robust performance across diverse and unseen target domains by learning the robust domain-invariant feat…
Autoencoder based approach for the mitigation of spurious correlations
Srinitish Srinivasan, Karthik Seemakurthy
Deep neural networks (DNNs) have exhibited remarkable performance across various tasks, yet their susceptibility to spurious correlations poses a significant challenge for out-of-d…
Domain Generalisation for Object Detection under Covariate and Concept Shift
Karthik Seemakurthy, Erchan Aptoula, Charles Fox +1
Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features, so that a model can generalise better to previously unse…