Unsupervised semantic discovery through visual patterns detection
This addresses the challenge of unsupervised semantic segmentation for computer vision researchers, though it appears incremental as it builds on existing methods with a new framework.
The paper tackles the problem of unsupervised semantic pattern discovery in images by proposing a fast method that hierarchically finds visual categories and produces segmentation masks, achieving optimal results in terms of robustness to noise and semantic consistency.
We propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the modeling of what is a visual pattern in an image, we introduce the notion of "semantic levels" and devise a conceptual framework along with measures and a dedicated benchmark dataset for future comparisons. Our algorithm is composed by two phases. A filtering phase, which selects semantical hotsposts by means of an accumulator space, then a clustering phase which propagates the semantic properties of the hotspots on a superpixels basis. We provide both qualitative and quantitative experimental validation, achieving optimal results in terms of robustness to noise and semantic consistency. We also made code and dataset publicly available.