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.
v-CLR: View-Consistent Learning for Open-World Instance Segmentation
Instance Migration Diffusion for Nuclear Instance Segmentation in Pathology
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities
Scene-Centric Unsupervised Panoptic Segmentation
CellVTA: Enhancing Vision Foundation Models for Accurate Cell Segmentation and Classification
RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety
Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
Foveated Instance Segmentation
Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery
Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines
HiRes-FusedMIM: A High-Resolution RGB-DSM Pre-trained Model for Building-Level Remote Sensing Applications
EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videos
A Temporal Modeling Framework for Video Pre-Training on Video Instance Segmentation
Should we pre-train a decoder in contrastive learning for dense prediction tasks?
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments
Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting
Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking
3D Hierarchical Panoptic Segmentation in Real Orchard Environments Across Different Sensors
Ship Detection in Remote Sensing Imagery for Arbitrarily Oriented Object Detection
CyclePose -- Leveraging Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence Microscopy
COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
SAS: Segment Any 3D Scene with Integrated 2D Priors
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
Segment Anything, Even Occluded
S4M: Segment Anything with 4 Extreme Points
TomatoScanner: phenotyping tomato fruit based on only RGB image
Joint 3D Point Cloud Segmentation using Real-Sim Loop: From Panels to Trees and Branches
AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model
Automatic Drywall Analysis for Progress Tracking and Quality Control in Construction
Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processing
Label-Efficient LiDAR Panoptic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.