Papers with Code · CC BY-SA 4.0
Instance Segmentation
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
데이터셋
108개COCO test-devFBMS-59COCO 2017 valOccluded COCOPhraseCutSeparated COCOObjectsRoomPASCAL VOC 2012 valScanNet200ScanNetV2ShapeStacksTBBRiSAIDBDD100K valCOCO 2017 valCOCO val (panoptic labels)RefCOCOShelf&Tote Training DatasetOoDISPASCAL VOC 2012PASCAL VOC 2012 valPartNetReferItScanNet++SceneNNCOCO 2017 valECSSDMEISMitoEMNYUDv2-IS