DeSTNet: Densely Fused Spatial Transformer Networks

07/11/2018
by   Roberto Annunziata, et al.
0

Modern Convolutional Neural Networks (CNN) are extremely powerful on a range of computer vision tasks. However, their performance may degrade when the data is characterised by large intra-class variability caused by spatial transformations. The Spatial Transformer Network (STN) is currently the method of choice for providing CNNs the ability to remove those transformations and improve performance in an end-to-end learning framework. In this paper, we propose Densely Fused Spatial Transformer Network (DeSTNet), which, to the best of our knowledge, is the first dense fusion pattern for combining multiple STNs. Specifically, we show how changing the connectivity pattern of multiple STNs from sequential to dense leads to more powerful alignment modules. Extensive experiments on three benchmarks namely, MNIST, GTSRB, and IDocDB show that the proposed technique outperforms related state-of-the-art methods (i.e., STNs and CSTNs) both in terms of accuracy and robustness.

READ FULL TEXT

page 7

page 8

page 9

page 14

page 15

page 16

research
03/30/2021

Rethinking Spatial Dimensions of Vision Transformers

Vision Transformer (ViT) extends the application range of transformers f...
research
03/09/2022

3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs

In this paper, we propose a novel multi-level aggregation network to reg...
research
06/05/2015

Spatial Transformer Networks

Convolutional Neural Networks define an exceptionally powerful class of ...
research
10/29/2018

Recurrent Transformer Networks for Semantic Correspondence

We present recurrent transformer networks (RTNs) for obtaining dense cor...
research
02/08/2021

TransReID: Transformer-based Object Re-Identification

In this paper, we explore the Vision Transformer (ViT), a pure transform...
research
08/12/2019

Jointly Aligning Millions of Images with Deep Penalised Reconstruction Congealing

Extrapolating fine-grained pixel-level correspondences in a fully unsupe...
research
12/12/2016

Inverse Compositional Spatial Transformer Networks

In this paper, we establish a theoretical connection between the classic...

Please sign up or login with your details

Forgot password? Click here to reset