“…1) Semi Supervision: Research on semi-supervised learning has mostly been conducted on the image classification setting [12], [13], [14], [15], [16], [17], [13], [18], [19], [20], [21], with interest in segmentation and object detection only rising recently [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39]. We follow these last set of works and characterize the semi supervision setting as: (upon sorting,) for a certain integer S, full labels are provided for images with indices 1 ≤ i ≤ S, and no labels for images with indices S < i ≤ M.…”