[CV2019/PaperSummary] YOLACT :Real-time Instance Segmentation

Yolact : Bounding Box with Instance Segmentation
Fig 1:Speed-performance trade-off for various instance segmentation methods on COCO.
Fig 2: YOLACT Architecture Blue/yellow indicates low/high values in the prototypes, gray nodes indicate functions that are not trained, and k = 4 in this example
Fig 3 : Protonet Architecture The labels denote feature size and channels for an image size of 550 × 550. Arrows indicate 3 × 3 conv layers, except for the final conv which is 1 × 1. The increase in size is an upsample followed by a conv
Eq1: Mask coefficient formulae
Fig 4 .Prototype Behavior The activations of the same six prototypes across different images. Prototypes 1, 4, and 5 are partition maps with boundaries clearly defined in image a, prototype 2 is a bottom-left directional map, prototype 3 segments out the background and provides instance contours, and prototype 6 segments out the ground.
Eq 2 : Lower triangle setting
Eq 3: Col wise max multiplication
Table 1 : Mask Performance We compare our approach to other state-of-the-art methods for mask mAP and speed on COCO test-dev.
Table 2 : Fast NMS Fast NMS performs only slightly worse than standard NMS
Table 3:Prototypes Choices for k in our method.
Fig 5 :YOLACT localization failure
Fig 6 : YOLACT leakage

Final Words ….

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store