4 papers
An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
Saurabh Saini, Kapil Ahuja, Thomas Wick +1
Optimization is essential in deep learning. The foundational method upon which most optimizers are built is momentum-based stochastic gradient descent. However, it suffers from two…
Block-Fused Attention-Driven Adaptively-Pooled ResNet Model for Improved Cervical Cancer Classification
Saurabh Saini, Kapil Ahuja, Akshat S. Chauhan
Cervical cancer is the second most common cancer among women and a leading cause of mortality. Many attempts have been made to develop an effective Computer Aided Diagnosis (CAD) s…
Accurate Thyroid Cancer Classification using a Novel Binary Pattern Driven Local Discrete Cosine Transform Descriptor
Saurabh Saini, Kapil Ahuja, Marc C. Steinbach +1
In this study, we develop a new CAD system for accurate thyroid cancer classification with emphasis on feature extraction. Prior studies have shown that thyroid texture is importan…
Prototype Guided Backdoor Defense
Venkat Adithya Amula, Sunayana Samavedam, Saurabh Saini +2
Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifica…