# A Simple and Generalist Approach for Panoptic Segmentation Source: [A Simple and Generalist Approach for Panoptic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:16:49.987Z Authors: Nedyalko Prisadnikov, Wouter Van Gansbeke, Danda Pani Paudel, Luc Van Gool Published: 2024-08-29T13:02:12.000Z ## Abstract Panoptic segmentation is an important computer vision task, where the current state-of-the-art solutions require specialized components to perform well. We propose a simple generalist framework based on a deep encoder - shallow decoder architecture with per-pixel prediction. Essentially fine-tuning a massively pretrained image model with minimal additional components. Naively this method does not yield good results. We show that this is due to imbalance during training and propose a novel method for reducing it - centroid regression in the space of spectral positional embeddings. Our method achieves panoptic quality (PQ) of 55.1 on the challenging MS-COCO dataset, state-of-the-art performance among generalist methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()