Using Large Text-to-Image Models with Structured Prompts for Skin Disease Identification: A Case Study

no code implementations • 17 Jan 2023 • Sajith Rajapaksa, Jean Marie Uwabeza Vianney, Renell Castro, Farzad Khalvati, Shubhra Aich

This paper investigates the potential usage of large text-to-image (LTI) models for the automated diagnosis of a few skin conditions with rarity or a serious lack of annotated datasets.

Optimized Global Perturbation Attacks For Brain Tumour ROI Extraction From Binary Classification Models

no code implementations • 9 Nov 2022 • Sajith Rajapaksa, Farzad Khalvati

In this work, we propose a weakly supervised approach to obtain regions of interest using binary class labels.

Binary Classification Segmentation

Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours

no code implementations • 29 Nov 2021 • Sajith Rajapaksa, Farzad Khalvati

Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipeline.

3D Classification Superpixels +1

Crop Lodging Prediction from UAV-Acquired Images of Wheat and Canola using a DCNN Augmented with Handcrafted Texture Features

1 code implementation • 18 Jun 2019 • Sara Mardanisamani, Farhad Maleki, Sara Hosseinzadeh Kassani, Sajith Rajapaksa, Hema Duddu, Menglu Wang, Steve Shirtliffe, Seungbum Ryu, Anique Josuttes, Ti Zhang, Sally Vail, Curtis Pozniak, Isobel Parkin, Ian Stavness, Mark Eramian

In this paper, we propose a deep convolutional neural network (DCNN) architecture for lodging classification using five spectral channel orthomosaic images from canola and wheat breeding trials.

General Classification Transfer Learning