Papers with Code 아카이브

Zero Shot Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 2
보존된 평가 기록: 17

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/microsoft/X-Decoder

공식 코드

Generalized Decoding for Pixel, Image, and Language

https://github.com/mschwimmbeck/hola

공식 코드

HOLa: HoloLens Object Labeling

https://github.com/mustafa1728/wlsegnet

공식 코드

A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentation

https://github.com/naver-ai/zim

공식 코드

ZIM: Zero-Shot Image Matting for Anything

https://github.com/nickjiang2378/vl-interp

공식 코드

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

https://github.com/nvlabs/odise

공식 코드

Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models

https://github.com/open-forest-observatory/tree-detection-framework

공식 코드

Zero-Shot Tree Detection and Segmentation from Aerial Forest Imagery

https://github.com/paulcouairon/diffcut

공식 코드

DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut

https://github.com/rafiibnsultan/geosam

공식 코드

GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation

https://github.com/robustsam/RobustSAM

공식 코드

RobustSAM: Segment Anything Robustly on Degraded Images

https://github.com/rt219/the-emergence-of-objectness

공식 코드

The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

https://github.com/sagieppel/matseg

공식 코드

Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data

https://github.com/shizenglin/training-free-object-counter

공식 코드

Training-free Object Counting with Prompts

https://github.com/showlab/datasetdm

공식 코드

DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models

https://github.com/syscv/sam-hq

공식 코드

Segment Anything in High Quality

https://github.com/timojl/clipseg

공식 코드

Image Segmentation Using Text and Image Prompts

https://github.com/tio-ikim/cellvit-plus-plus

공식 코드

CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Models

https://github.com/ustb-ai3dvip/matsam

공식 코드

MatSAM: Efficient Extraction of Microstructures of Materials via Visual Large Model

https://github.com/vbmaq/et-sam

공식 코드

Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)

https://github.com/vcg/ffd4denspineem

공식 코드

Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures

https://github.com/walbouss/gem

공식 코드

Grounding Everything: Emerging Localization Properties in Vision-Language Transformers

https://github.com/wangyunpengbio/x-recon

공식 코드

X-Recon: Learning-based Patient-specific High-Resolution CT Reconstruction from Orthogonal X-Ray Images

https://github.com/wujunde/promptunet

공식 코드

One-Prompt to Segment All Medical Images

https://github.com/xhu248/autosam

공식 코드

How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images

https://github.com/xiaozhen228/vcp-clip

공식 코드

VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation

https://github.com/xmed-lab/clip_surgery

공식 코드

A Closer Look at the Explainability of Contrastive Language-Image Pre-training

https://github.com/yichizhang98/sam4mis

공식 코드

Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey

https://github.com/ymgw55/scesame

공식 코드

Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation

https://github.com/yuhoo0302/segment-anything-model-for-medical-images

공식 코드

Segment Anything Model for Medical Images?

https://github.com/zimingzhong/MeshSegmenter

공식 코드

MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.