CollaGAN : Collaborative GAN for Missing Image Data Imputation - Dongwook Lee - CVPR 2019
Info
Title: CollaGAN : Collaborative GAN for Missing Image Data Imputation
Task: Image Generation
Author: Dongwook Lee
Arxiv: 1829
Published: CVPR 2019
Highlights
Many-to-One image generation: The underlying image manifold can be learned more synergistically from the multiple input data set sharing the same manifold structure, rat...
Using Docker Remote Interpreter in PyCharm on Linux
Note: This functionality is only available for Professional version of PyCharm
Step 1: Export Docker Daemon via TCP
# stop docker service
sudo service docker stop
# export daemon
sudo dockerd -H unix:///var/run/docker.sock -H tcp://127.0.0.1:2375
The Docker daemon can listen for Docker Engine API requests via three different types of Socket...
U-GAT-IT: TensorFlow Implementation
Info
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
Junho Kim (NCSOFT), Minjae Kim (NCSOFT), Hyeonwoo Kang (NCSOFT), Kwanghee Lee (Boeing Korea)
Abstract *
We propose a novel method for unsupervised image-to-image translation, which incorporates a new attenti...
U-GAT-IT: PyTorch Implementation
Info
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
Junho Kim (NCSOFT), Minjae Kim (NCSOFT), Hyeonwoo Kang (NCSOFT), Kwanghee Lee (Boeing Korea)
Abstract *
We propose a novel method for unsupervised image-to-image translation, which incorporates a new attentio...
DLOW: Domain Flow for Adaptation and Generalization - Rui Gong - CVPR 2019
Info
Title: DLOW: Domain Flow for Adaptation and Generalization
Task: Image Generation, Domain Adaptation
Author: Rui Gong, Wen Li, Yuhua Chen, Luc Van Gool
Arxiv: 1812.05418
Published: CVPR 2019
Highlights
The DLOW model is able to produce a sequence of intermediate domains shifting from the source domain to the target domain.
...
Bounding Box(BBOX) IOU Calculation and Transformation in PyTorch
Object Detection: Calculating IOU
Calculate overlap between two set of bboxes
If is_aligned is False, then calculate the ious between each bbox
of bboxes1 and bboxes2, otherwise the ious between each aligned pair of
bboxes1 and bboxes2.
Args:
bboxes1 (Tensor): shape (m, 4)
bboxes2 (Tensor): shape (n, ...
Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping - Huan Fu - CVPR 2019
Info
Title: Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
Task: Image Generation
Author: Chaohui Wang, Huan Fu, Mingming Gong, Kayhan Batmanghelich, Kun Zhang, Dacheng Tao
Arxiv: 1809.05852
Published: CVPR 2019
Abstract
Unsupervised domain mapping aims to learn a function to transla...
Object Detection: Anchor Generator in PyTorch
2-stage Anchor Generator: Fast RCNN, Faster RCNN, Mask RCNN
class AnchorGenerator(object):
def __init__(self, base_size, scales, ratios, scale_major=True, ctr=None):
self.base_size = base_size
self.scales = torch.Tensor(scales)
self.ratios = torch.Tensor(ratios)
self.scale_major = scale_major
self.ct...
130 post articles, 17 pages.