Bridging Structure and Appearance: Topological Features for Robust Self-Supervised Segmentation
This addresses robustness issues in self-supervised segmentation for computer vision applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of self-supervised semantic segmentation failing due to appearance ambiguities by proposing GASeg, a framework that leverages topological information to bridge geometry and appearance, achieving state-of-the-art performance on benchmarks like COCO-Stuff, Cityscapes, and PASCAL.
Self-supervised semantic segmentation methods often fail when faced with appearance ambiguities. We argue that this is due to an over-reliance on unstable, appearance-based features such as shadows, glare, and local textures. We propose \textbf{GASeg}, a novel framework that bridges appearance and geometry by leveraging stable topological information. The core of our method is Differentiable Box-Counting (\textbf{DBC}) module, which quantifies multi-scale topological statistics from two parallel streams: geometric-based features and appearance-based features. To force the model to learn these stable structural representations, we introduce Topological Augmentation (\textbf{TopoAug}), an adversarial strategy that simulates real-world ambiguities by applying morphological operators to the input images. A multi-objective loss, \textbf{GALoss}, then explicitly enforces cross-modal alignment between geometric-based and appearance-based features. Extensive experiments demonstrate that GASeg achieves state-of-the-art performance on four benchmarks, including COCO-Stuff, Cityscapes, and PASCAL, validating our approach of bridging geometry and appearance via topological information.