Papers with Code · CC BY-SA 4.0

Instance Segmentation

916 평가 기록 108 datasets

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

하위 태스크

RE Referring Expression Segmentation 23 데이터셋 · 330 rows 3I 3D Instance Segmentation 11 데이터셋 · 81 rows UO Unsupervised Object Segmentation 9 데이터셋 · 53 rows RI Real-time Instance Segmentation 8 데이터셋 · 32 rows IS Image-level Supervised Instance Segmentation 3 데이터셋 · 26 rows HI Human Instance Segmentation 2 데이터셋 · 19 rows BI Box-supervised Instance Segmentation 2 데이터셋 · 12 rows 3S 3D Semantic Instance Segmentation 2 데이터셋 · 6 rows PI Point-Supervised Instance Segmentation 3 데이터셋 · 6 rows RI RGB-D Instance Segmentation 3 데이터셋 · 5 rows AI Amodal Instance Segmentation 1 데이터셋 · 2 rows OI Open-World Instance Segmentation 1 데이터셋 · 2 rows UO Unseen Object Instance Segmentation 2 데이터셋 · 2 rows OI One-Shot Instance Segmentation 1 데이터셋 · 1 rows SP Semi-Supervised Person Instance Segmentation 1 데이터셋 · 1 rows AI Anomaly Instance Segmentation 0 데이터셋 · 0 rows SC Solar Cell Segmentation 0 데이터셋 · 0 rows