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 | Co-DETR (single-scale) | mask AP | 60.7 | — | Unverified |
| 2 | EVA | mask AP | 55 | — | Unverified |
| 3 | HTC-ealrystop-ema | mask AP | 50.4 | — | Unverified |
| 4 | GLEE-Pro | mask AP | 49.9 | — | Unverified |
| 5 | ViTDet-H | mask AP | 48.1 | — | Unverified |
| 6 | ViTDet-L | mask AP | 46 | — | Unverified |
| 7 | DiverGen (Swin-L) | mask AP | 45.5 | — | Unverified |
| 8 | CenterNet2 (Swin-L w/ X-Paste + Copy-Paste) | mask AP | 45.4 | — | Unverified |
| 9 | DiffusionInst-SwinL | mask AP | 38.6 | — | Unverified |
| 10 | FRACAL-Swin-B | mask AP | 38.5 | — | Unverified |