9 citations · 22 across the 12 of their papers we have counts for
7 papers · 1 filter
CornViT: A Multi-Stage Convolutional Vision Transformer Framework for Hierarchical Corn Kernel Analysis
Sai Teja Erukude, Jane Mascarenhas, Lior Shamir
Accurate grading of corn kernels is critical for seed certification, directional seeding, and breeding, yet it is still predominantly performed by manual inspection. This work intr…
FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data
Viswa Chaitanya Marella, Suhasnadh Reddy Veluru, Sai Teja Erukude
Federated Learning (FL) allows multiple institutions to cooperatively train machine learning models while retaining sensitive data at the source, which has great utility in privacy…
Explainable Deep Learning in Medical Imaging: Brain Tumor and Pneumonia Detection
Sai Teja Erukude, Viswa Chaitanya Marella, Suhasnadh Reddy Veluru
Deep Learning (DL) holds enormous potential for improving medical imaging diagnostics, yet the lack of interpretability in most models hampers clinical trust and adoption. This pap…
Wavelet-based GAN Fingerprint Detection using ResNet50
Sai Teja Erukude, Suhasnadh Reddy Veluru, Viswa Chaitanya Marella
Identifying images generated by Generative Adversarial Networks (GANs) has become a significant challenge in digital image forensics. This research presents a wavelet-based detecti…
Fourier-Based GAN Fingerprint Detection using ResNet50
Sai Teja Erukude, Viswa Chaitanya Marella, Suhasnadh Reddy Veluru
The rapid rise of photorealistic images produced from Generative Adversarial Networks (GANs) poses a serious challenge for image forensics and industrial systems requiring reliable…
Identifying bias in CNN image classification using image scrambling and transforms
Sai Teja Erukude
CNNs are now prevalent as the primary choice for most machine vision problems due to their superior rate of classification and the availability of user-friendly libraries. These ne…
Identifying Bias in Deep Neural Networks Using Image Transforms
Sai Teja Erukude, Akhil Joshi, Lior Shamir
CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user…