Description
DeepMask is an object proposal algorithm based on a convolutional neural network. Given an input image patch, DeepMask generates a class-agnostic mask and an associated score which estimates the likelihood of the patch fully containing a centered object (without any notion of an object category). The core of the model is a ConvNet which jointly predicts the mask and the object score. A large part of the network is shared between those two tasks: only the last few network layers are specialized for separately outputting a mask and score prediction.
Papers Using This Method
Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction2020-05-19DeepMask: an algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual network2019-11-09Learning to Segment Object Candidates via Recursive Neural Networks2016-12-04A MultiPath Network for Object Detection2016-04-07Learning to Refine Object Segments2016-03-29Instance-sensitive Fully Convolutional Networks2016-03-29