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.
Source: Learning to Segment Object Candidates via Recursive Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 3 | 21.43% |
Object | 3 | 21.43% |
Instance Segmentation | 2 | 14.29% |
Object Detection | 2 | 14.29% |
Optical Flow Estimation | 1 | 7.14% |
Cloud Detection | 1 | 7.14% |
Shadow Detection | 1 | 7.14% |
Object Proposal Generation | 1 | 7.14% |
Component | Type |
|
---|---|---|
![]() |
Convolutions | |
![]() |
Convolutions | |
![]() |
Regularization | |
![]() |
Pooling Operations | |
![]() |
Activation Functions | |
![]() |
Convolutional Neural Networks |