Panoptic segmentation unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance).
( Image credit: Detectron2 )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
While image classification models have recently continued to advance, most downstream applications such as object detection and semantic segmentation still employ ResNet variants as the backbone network due to their simple and modular structure.
SOTA for Semantic Segmentation on ADE20K
In this technical report, we present two novel datasets for image scene understanding.
Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
#5 best model for Instance Segmentation on COCO test-dev
In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances.
We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively.
#3 best model for Instance Segmentation on COCO test-dev (AP50 metric)
The generator/evaluator approach for this case consists of two independent convolutional neural nets: a generator net that suggests variety segments corresponding to objects, stuff and parts regions in the image, and an evaluator net that chooses the best segments to be merged into the segmentation map.
In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results.
#2 best model for Panoptic Segmentation on KITTI Panoptic Segmentation