Papers with Code 아카이브
Instance Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 17
- 평가표
- 36
- 보존된 평가 기록
- 338
Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.
Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
gen2seg: Generative Models Enable Generalizable Instance Segmentation
UWSAM: Segment Anything Model Guided Underwater Instance Segmentation and A Large-scale Benchmark Dataset
Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
Instance Segmentation for Point Sets
Enhancing Transformers Through Conditioned Embedded Tokens
FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
SoftPQ: Robust Instance Segmentation Evaluation via Soft Matching and Tunable Thresholds
Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
SurgPose: Generalisable Surgical Instrument Pose Estimation using Zero-Shot Learning and Stereo Vision
The RaspGrade Dataset: Towards Automatic Raspberry Ripeness Grading with Deep Learning
Vision Foundation Model Embedding-Based Semantic Anomaly Detection
Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model
RepSNet: A Nucleus Instance Segmentation model based on Boundary Regression and Structural Re-parameterization
Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer
Self-Supervised Learning for Robotic Leaf Manipulation: A Hybrid Geometric-Neural Approach
A Novel WaveInst-based Network for Tree Trunk Structure Extraction and Pattern Analysis in Forest Inventory
RESAnything: Attribute Prompting for Arbitrary Referring Segmentation
Global Collinearity-aware Polygonizer for Polygonal Building Mapping in Remote Sensing
MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection
OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation
Object Learning and Robust 3D Reconstruction
NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation
Occlusion-Ordered Semantic Instance Segmentation
3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation
CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting
Single-shot Star-convex Polygon-based Instance Segmentation for Spatially-correlated Biomedical Objects
CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image
Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation
P2Object: Single Point Supervised Object Detection and Instance Segmentation
Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian Splatting
BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
S^4M: Boosting Semi-Supervised Instance Segmentation with SAM
APSeg: Auto-Prompt Model with Acquired and Injected Knowledge for Nuclear Instance Segmentation and Classification
Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.