返回
Recurrent Affine Transform Encoder for Image Representation
DOI:10.1109/ACCESS.2022.3150340.png)
摘要
En 中文
This paper proposes a Recurrent Affine Transform Encoder (RATE) that can be used for image representation learning. We propose a learning architecture that enables a CNN encoder to learn the affine transform parameter of images. The proposed learning architecture decomposes an affine transform matrix into two transform matrices and learns them jointly in a self-supervised manner. The proposed RATE is trained by unlabeled image data without any ground truth and infers the affine transform parameter of input images recurrently. The inferred affine transform parameter can be used to represent images in canonical form to greatly reduce the image variations in affine transforms such as rotation, scaling, and translation. Different from the spatial transformer network, the proposed RATE does not need to be embedded into other networks for training with the aid of other learning objectives. We show that the proposed RATE learns the affine transform parameter of images and achieves impressive image representation results in terms of invariance to translation, scaling, and rotation. We also show that the classification performance is enhanced and is more robust against distortion by incorporating the RATE into the existing classification model.
Keyword:
Transforms
Training
Transformers
Matrix decomposition
Task analysis
Image representation
Feature extraction
Canonical image base
self-supervised learning
representation learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍?
Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉,互穿网络中具有变构效应的晶态反应

