Agriculture plays a crucial role in any nation’s overall growth, as it feeds the whole nation without which it is not possible to make any kind of development. It has also a major contribution to the country’s GDP (Gross Domestic Product), especially in developing nations. Instead of knowing this, every year a major portion of the agriculture is damaged by disease in plants, pests, and other reasons. As we cannot control the external natural factors, but we can definitely control the loss of this agricultural loss due to diseases in the plants and pests. In this paper we will examine the deep learning, machine learning, and transfer learning in the detection of disease in cauliflower plant. Then discuss the recent development in deep learning, machine learning, and transfer learning for the plant disease detection, and also address the main issues which need further study in this field to enhance the accuracy and performance of the different algorithms to detect the disease in cauliflower. We will study the different algorithms that are performing well for other plants in disease detection and then try to use those algorithms for our study and find which algorithm is performing best for disease detection in cauliflower for our study. Which will help farmers to increase the yield of the crop.