Budget-aware Semi-Supervised Semantic and Instance Segmentation
This work addresses the annotation cost problem for image segmentation researchers and practitioners, presenting an incremental improvement by unifying comparison based on total annotation budget.
The paper tackles the problem of reducing annotation burden in image segmentation by proposing a budget-aware semi-supervised approach that outperforms weakly-supervised methods at low annotation budgets and previous semi-supervised works with reduced labeling cost, demonstrating results on Pascal VOC benchmark.
Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision, e.g. image-level labels or bounding boxes. Another option are semi-supervised settings, that commonly leverage a few strong annotations and a huge number of unlabeled/weakly-labeled data. In this paper, we revisit semi-supervised segmentation schemes and narrow down significantly the annotation budget (in terms of total labeling time of the training set) compared to previous approaches. With a very simple pipeline, we demonstrate that at low annotation budgets, semi-supervised methods outperform by a wide margin weakly-supervised ones for both semantic and instance segmentation. Our approach also outperforms previous semi-supervised works at a much reduced labeling cost. We present results for the Pascal VOC benchmark and unify weakly and semi-supervised approaches by considering the total annotation budget, thus allowing a fairer comparison between methods.