Spatial Transformer Networks

, , ,  -

Publications: arXiv Add/Edit

Abstract: Add/Edit

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network. This differentiable module can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimisation process. We show that the use of spatial transformers results in models which learn invariance to translation, scale, rotation and more generic warping, resulting in state-of-the-art performance on several benchmarks, and for a number of classes of transformations.

Keywords: Add/Edit


Code Links

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Inverse Compositional Spatial Transformer Networks (CVPR 2017)

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

implement spatial transformer networks with mnist

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

CRNN(Convolutional Recurrent Neural Network), with optional STN(Spatial Transformer Network), in Tensorflow, multi-gpu supported.

0

Languages: Lua Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Modules for spatial transformer networks (BHWD layout)

0

Languages: Lua Add/Edit

Libraries: Add/Edit

Description: Add/Edit

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Chainer implementation of "Spatial Transformer Network"

0
github.com: /SkafteNicki/ddtn

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Repository for our upcoming code, that we used for our "Deep diffeomorphic transformer networks" paper (Accepted to CVPR 2018). Will be update during the spring of 2018.

0

Languages: Cuda Add/Edit

Libraries: Add/Edit

Description: Add/Edit

3D Spatial Transformer Network

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Pytorch Implementation of Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Additional Layers for Keras-Tensorflow

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

pytorch version of spatial transformer networks

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

0

Languages: Lua Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Spatial Transformer Network with Mnist

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

RF Spatial Transformer Network

0
github.com: /renato145/stn

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Spatial Transformer Networks

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Tensorflow Implementation of Spatial Transformer Networks

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

A Chainer implementation of Spatial Transformer Networks trained on MNIST

0

Languages: Shell Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Train a neural network component that can add spatial transformations such as translation and rotation to larger models.

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Application of Spatial transformer network to a hand alignment task.

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

German Traffic Sign Recognition Benchmark, Keras implementation with Spatial Transformer Networks

0

Languages: C++ Add/Edit

Libraries: Add/Edit

Description: Add/Edit

there are eight flies about Spatial Transformer Networks

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Pure Tensorflow Implementation of Spatial Transformer Networks. TF API 1.0. Good visualization. Easy to be intergrated.

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

TensorFlow implementation of Thin Plate Spline Spatial Transformer Network

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Implementation of spatial transformer networks (STNs) in keras 2 with tensorflow as backend.

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Tensorflow models for Spatial Transformer Networks

0

Languages: Lua Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Traffic sign recognition with Torch

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Code etc for Hacker Dojo Deep Learning Study Group

0

Languages: C++ Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Spatial Transformer Networks

0
github.com: /Sooram/stn

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

a implementation of spatial transformer network

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Tensorflow implementation of spatial transformer network for 2d/3d image and supports affine/non-rigid transformation

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Code for Recurrent Spatial Transformer Networks

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Thin Plate Spline Spatial Transformer Network implementation with TensorFlow

0

Languages: C++ Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Implement Spatial Transformer Networks with TPS transformation by Caffe

0
github.com: /eonr/CompVision

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Some of my computer vision notebooks

0

Languages: Matlab Add/Edit

Libraries: Add/Edit

Description: Add/Edit

MatConvNet implementation for incorporating a 3D Morphable Model (3DMM) into a Spatial Transformer Network (STN)

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

A Tensorflow Implementation of Spatial Transformer Networks

0

Languages: C++ Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Spatial Transformer Network Implementation in Caffe

0

Languages: Jupyter Notebook Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Pytorch code for spatial transformer network with mask

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Bringing up some extra Cosmo to Keras.

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Spatial Transformer network

0