LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
This addresses the problem of accurate segmentation in open-vocabulary scenarios for computer vision applications, representing an incremental improvement over existing training-free methods.
The paper tackles open-vocabulary semantic segmentation by proposing a training-free method that enhances Vision-and-Language Model predictions using label propagation over patches and pixels, achieving state-of-the-art performance among training-free methods across diverse datasets.
We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS