Papers with Code 아카이브
Universal Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SemiSAM+: Rethinking Semi-Supervised Medical Image Segmentation in the Era of Foundation Models
SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images
MedicoSAM: Towards foundation models for medical image segmentation
FOCUS: Towards Universal Foreground Segmentation
VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
HyperSeg: Towards Universal Visual Segmentation with Large Language Model
Large Language Model with Region-guided Referring and Grounding for CT Report Generation
Rethinking the Evaluation of Visible and Infrared Image Fusion
MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Beyond Human Vision: The Role of Large Vision Language Models in Microscope Image Analysis
RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
COCONut: Modernizing COCO Segmentation
SegICL: A Multimodal In-context Learning Framework for Enhanced Segmentation in Medical Imaging
One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts
Unsupervised Universal Image Segmentation
Universal Segmentation at Arbitrary Granularity with Language Instruction
Hierarchical Open-vocabulary Universal Image Segmentation
CLUSTSEG: Clustering for Universal Segmentation
Segment Everything Everywhere All at Once
UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner
Towards Universal Vision-language Omni-supervised Segmentation
OneFormer: One Transformer to Rule Universal Image Segmentation
Training a universal instance segmentation network for live cell images of various cell types and imaging modalities
Universal Segmentation of 33 Anatomies
Masked-attention Mask Transformer for Universal Image Segmentation
Dynamic-structured Semantic Propagation Network
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.