A Simple and Generalist Approach for Panoptic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915185667604480 |
|---|---|
| author | Prisadnikov, Nedyalko Van Gansbeke, Wouter Paudel, Danda Pani Van Gool, Luc |
| author_facet | Prisadnikov, Nedyalko Van Gansbeke, Wouter Paudel, Danda Pani Van Gool, Luc |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16504 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Simple and Generalist Approach for Panoptic Segmentation Prisadnikov, Nedyalko Van Gansbeke, Wouter Paudel, Danda Pani Van Gool, Luc Computer Vision and Pattern Recognition 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. |
| title | A Simple and Generalist Approach for Panoptic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.16504 |