In this paper, a simple topology of Capsule Network (CapsNet) is investigated
for the problem of image colorization. The generative and segmentation
capabilities of the original CapsNet topology, which is proposed for image
classification problem, is leveraged for the colorization of the images by
modifying the network as follows:1) The original CapsNet model is adapted to
map the grayscale input to the output in the CIE Lab colorspace, 2) The feature
detector part of the model is updated by using deeper feature layers inherited
from VGG-19 pre-trained model with weights in order to transfer low-level image
representation capability to this model, 3) The margin loss function is
modified as Mean Squared Error (MSE) loss to minimize the
image-to-imagemapping. The resulting CapsNet model is named as Colorizer
Capsule Network (ColorCapsNet).The performance of the ColorCapsNet is evaluated
on the DIV2K dataset and promising results are obtained to investigate Capsule
Networks further for image colorization problem.

本研究探讨了一种简单的 Capsule 网络 (CapsNet) 拓扑结构，用于图像着色问题。通过修改网络结构，将这个原本用于图像分类问题的 CapsNet 模型适用于 CIE Lab 颜色空间下灰度图像到彩色图像的生成和分割任务，利用 VGG-19 预训练模型的深度特征层次和 Mean Squared Error loss 函数进行改进优化，获得了不错的结果。

胶囊网络图像彩色化

Image Colorization By Capsule Networks

This paper introduces a novel feature detector based only on information
embedded inside a CNN trained on standard tasks (e.g. classification). While
previous works already show that the features of a trained CNN are suitable
descriptors, we show here how to extract the feature locations from the network
to build a detector. This information is computed from the gradient of the
feature map with respect to the input image. This provides a saliency map with
local maxima on relevant keypoint locations. Contrary to recent CNN-based
detectors, this method requires neither supervised training nor finetuning. We
evaluate how repeatable and how matchable the detected keypoints are with the
repeatability and matching scores. Matchability is measured with a simple
descriptor introduced for the sake of the evaluation. This novel detector
reaches similar performances on the standard evaluation HPatches dataset, as
well as comparable robustness against illumination and viewpoint changes on
Webcam and photo-tourism images. These results show that a CNN trained on a
standard task embeds feature location information that is as relevant as when
the CNN is specifically trained for feature detection.

本研究引入了一种基于 CNN 内部信息的新型特征检测器，检测器的信息从特征图与输入图像的梯度计算获得，能够生成显著性地图和相关关键点，无需监督训练，和专门的 feature detector 性能相似。

预训练 CNN 的嵌入式特征本地化

ELF: Embedded Localisation of Features in pre-trained CNN

In this work we address the problem of finding reliable pixel-level
correspondences under difficult imaging conditions. We propose an approach
where a single convolutional neural network plays a dual role: It is
simultaneously a dense feature descriptor and a feature detector. By postponing
the detection to a later stage, the obtained keypoints are more stable than
their traditional counterparts based on early detection of low-level
structures. We show that this model can be trained using pixel correspondences
extracted from readily available large-scale SfM reconstructions, without any
further annotations. The proposed method obtains state-of-the-art performance
on both the difficult Aachen Day-Night localization dataset and the InLoc
indoor localization benchmark, as well as competitive performance on other
benchmarks for image matching and 3D reconstruction.

本文提出了一种使用卷积神经网络在像素级别取得可靠对应的方法，该模型可以同时作为密集特征描述符和特征检测器，并且在后期检测可以获得比传统低级结构的更稳定的关键点，从而实现了在无法获取更多注释信息的情况下训练该模型，该方法可以在难以定位的数据集（Aachen Day-Night localization dataset）和室内定位测试基准（InLoc indoor localization benchmark）中获得最先进的表现，同时在其他图像匹配和 3D 重建基准测试中也有竞争力。