StructToken : Rethinking Semantic Segmentation with Structural Prior
This addresses the problem of ignoring structural information in semantic segmentation for computer vision applications, representing a new paradigm rather than an incremental improvement.
The paper tackles semantic segmentation by introducing a structure-aware extraction paradigm that uses learned structure tokens to interact with image features, achieving state-of-the-art results on benchmarks like ADE20K, Cityscapes, and COCO-Stuff-10K.
In previous deep-learning-based methods, semantic segmentation has been regarded as a static or dynamic per-pixel classification task, \textit{i.e.,} classify each pixel representation to a specific category. However, these methods only focus on learning better pixel representations or classification kernels while ignoring the structural information of objects, which is critical to human decision-making mechanism. In this paper, we present a new paradigm for semantic segmentation, named structure-aware extraction. Specifically, it generates the segmentation results via the interactions between a set of learned structure tokens and the image feature, which aims to progressively extract the structural information of each category from the feature. Extensive experiments show that our StructToken outperforms the state-of-the-art on three widely-used benchmarks, including ADE20K, Cityscapes, and COCO-Stuff-10K.