Recently, there has been significant interest in various supervised machine learning techniques that can help reduce the time and effort consumed by manual interpretation workflows. However, most successful supervised machine learning algorithms require huge amounts of annotated training data. Obtaining these labels for large seismic volumes is a very time-consuming and laborious task. We have addressed this problem by presenting a weakly supervised approach for predicting the labels of various seismic structures. By having an interpreter select a very small number of exemplar images for every class of subsurface structures, we use a novel similarity-based retrieval technique to extract thousands of images that contain similar subsurface structures from the seismic volume. By assuming that similar images belong to the same class, we obtain thousands of image-level labels for these images; we validate this assumption. We have evaluated a novel weakly supervised algorithm for mapping these rough image-level labels into more accurate pixel-level labels that localize the different subsurface structures within the image. This approach dramatically simplifies the process of obtaining labeled data for training supervised machine learning algorithms on seismic interpretation tasks. Using our method, we generate thousands of automatically labeled images from the Netherlands Offshore F3 block with reasonably accurate pixel-level labels. We believe that this work will allow for more advances in machine learning-enabled seismic interpretation.