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 | 27.27% |
Instance Segmentation | 2 | 18.18% |
Object Detection | 2 | 18.18% |
Optical Flow Estimation | 1 | 9.09% |
Cloud Detection | 1 | 9.09% |
Shadow Detection | 1 | 9.09% |
Object Proposal Generation | 1 | 9.09% |
Component | Type |
|
---|---|---|
1x1 Convolution
|
Convolutions | |
Convolution
|
Convolutions | |
Dropout
|
Regularization | |
Max Pooling
|
Pooling Operations | |
ReLU
|
Activation Functions | |
VGG
|
Convolutional Neural Networks |