YOLACT: Real-Time Instance Segmentation [ICCV Trailer]

GitHub: Paper: See you at ICCV, be there or be square. All results were computed in real-time using 1 RTX 2080 Ti. No temporal smoothing was applied (just pass each frame individually through the network). The only training data used was COCO’s 2017 train set. We did not augment our data with motion blur (though that would probably be a good idea). All videos had the same hyperparameters, and if you want to produce exactly what you see here