Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace
This work addresses the problem of reducing annotation costs for semantic segmentation in computer vision, offering a direct scribble-based approach without extra data or constraints, though it is incremental in improving existing scribble-supervised methods.
The paper tackles scribble-supervised semantic segmentation by reducing prediction uncertainty through entropy minimization and random walks on neural representations, and imposing consistency via self-supervision on neural eigenspace, achieving results comparable to some fully supervised methods and robustness to scribble degradation.
Scribble-supervised semantic segmentation has gained much attention recently for its promising performance without high-quality annotations. Due to the lack of supervision, confident and consistent predictions are usually hard to obtain. Typically, people handle these problems to either adopt an auxiliary task with the well-labeled dataset or incorporate the graphical model with additional requirements on scribble annotations. Instead, this work aims to achieve semantic segmentation by scribble annotations directly without extra information and other limitations. Specifically, we propose holistic operations, including minimizing entropy and a network embedded random walk on neural representation to reduce uncertainty. Given the probabilistic transition matrix of a random walk, we further train the network with self-supervision on its neural eigenspace to impose consistency on predictions between related images. Comprehensive experiments and ablation studies verify the proposed approach, which demonstrates superiority over others; it is even comparable to some full-label supervised ones and works well when scribbles are randomly shrunk or dropped.