1. Vistr[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
2. Solov2SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)
3. SoloSOLO: Segmenting Objects by Locations
4. CondinstConditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val
5. Yolact fcosYOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val