Universal Segmentation
9 papers with code • 0 benchmarks • 0 datasets
Universal segmentation is a challenging computer vision task that aims to segment images into semantic regions, regardless of the task or the domain. It requires the model to learn a wide range of visual concepts and to be able to generalize to new tasks and domains.
Benchmarks
These leaderboards are used to track progress in Universal Segmentation
Libraries
Use these libraries to find Universal Segmentation models and implementationsMost implemented papers
Masked-attention Mask Transformer for Universal Image Segmentation
While only the semantics of each task differ, current research focuses on designing specialized architectures for each task.
OneFormer: One Transformer to Rule Universal Image Segmentation
However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance.
Segment Everything Everywhere All at Once
In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
Training a universal instance segmentation network for live cell images of various cell types and imaging modalities
We share our recent findings in an attempt to train a universal segmentation network for various cell types and imaging modalities.
UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation.
CLUSTSEG: Clustering for Universal Segmentation
We present CLUSTSEG, a general, transformer-based framework that tackles different image segmentation tasks (i. e., superpixel, semantic, instance, and panoptic) through a unified neural clustering scheme.
Hierarchical Open-vocabulary Universal Image Segmentation
Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions.
Universal Segmentation at Arbitrary Granularity with Language Instruction
This paper aims to achieve universal segmentation of arbitrary semantic level.
Unsupervised Universal Image Segmentation
Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e. g., STEGO) or class-agnostic instance segmentation (e. g., CutLER), but not both (i. e., panoptic segmentation).