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
Papers
Showing 1–10 of 2262 papers
All datasetsCOCO test-devCOCO minivalLVIS v1.0 valCityscapes valADE20K valARMBenchOccluded COCOOoDISSeparated COCOTBBRBDD100K valCOCO val (panoptic labels)
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) | mask AP | 49 | — | Unverified |
| 2 | OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained) | mask AP | 48.7 | — | Unverified |
| 3 | OpenSeeD( SwinL, single-scale) | mask AP | 48.5 | — | Unverified |
| 4 | AFF-Base (single-scale, point-based Mask2Former) | mask AP | 46.2 | — | Unverified |
| 5 | OneFormer (DiNAT-L, single-scale) | mask AP | 45.6 | — | Unverified |
| 6 | OneFormer (Swin-L, single-scale) | mask AP | 45.6 | — | Unverified |
| 7 | DiNAT-L (single-scale, Mask2Former) | mask AP | 45.1 | — | Unverified |
| 8 | AFF-Small (single-scale, point-based Mask2Former) | mask AP | 44 | — | Unverified |
| 9 | Mask2Former (Swin-L, single-scale) | mask AP | 43.7 | — | Unverified |
| 10 | Mask2Former (Swin-B) | mask AP | 42 | — | Unverified |