OMG-Seg: Is One Model Good Enough For All Segmentation?
This work addresses the need for a unified segmentation model to simplify deployment and reduce resource usage across multiple computer vision tasks, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of unifying various segmentation tasks, traditionally handled by separate models, into a single model called OMG-Seg, which efficiently supports over ten tasks including image and video segmentation types, achieving satisfactory performance while reducing computational and parameter overhead.
In this work, we address various segmentation tasks, each traditionally tackled by distinct or partially unified models. We propose OMG-Seg, One Model that is Good enough to efficiently and effectively handle all the segmentation tasks, including image semantic, instance, and panoptic segmentation, as well as their video counterparts, open vocabulary settings, prompt-driven, interactive segmentation like SAM, and video object segmentation. To our knowledge, this is the first model to handle all these tasks in one model and achieve satisfactory performance. We show that OMG-Seg, a transformer-based encoder-decoder architecture with task-specific queries and outputs, can support over ten distinct segmentation tasks and yet significantly reduce computational and parameter overhead across various tasks and datasets. We rigorously evaluate the inter-task influences and correlations during co-training. Code and models are available at https://github.com/lxtGH/OMG-Seg.