PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modification - Salimans - ICLR 2017 - TensorFlow Code
Info
Title: PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
Task: Image Generation
Author: T. Salimans, A. Karpathy, X. Chen, and D. P. Kingma
Date: Jan. 2017
Arxiv: 1701.05517
Published: ICLR 2017
Affiliation: OpenAI
Highlights & Drawbacks
A discretized logistic mi...
Conditional Image Generation with PixelCNN Decoders - van den Oord - NIPS 2016 - TensorFlow & PyTorch Code
Info
Title: Conditional Image Generation with PixelCNN Decoders
Task: Image Generation
Author: A. van den Oord, N. Kalchbrenner, O. Vinyals, L. Espeholt, A. Graves, and K. Kavukcuoglu
Date: Jun. 2016
Arxiv: 1606.05328
Published: NIPS 2016
Affiliation: Google DeepMind
Highlights & Drawbacks
Conditional with class labels o...
Object Detection Must Reads(Part 1): Fast RCNN, Faster RCNN, R-FCN and FPN
Fast RCNN - Grishick - ICCV 2015 - Caffe Code
Info
Title: Fast RCNN
Task: Object Detection
Author: Ross Girshick
Arxiv: 1504.08083
Date: April 2015
Published: ICCV 2015
Highlights
An improvement to [R-CNN] (https://blog.ddlee.cn/posts/415f4992/), ROI Pooling Design
Article structure is clear
R-CNN’s Drawbacks
Training i...
(PixelRNN & PixelCNN)Pixel Recurrent Neural Networks - van den Oord - ICML 2016
Info
Title: Pixel Recurrent Neural Networks
Task: Image Generation
Author: A. van den Oord, N. Kalchbrenner, and K. Kavukcuoglu
Date: Jan 2016
Arxiv: 1601.06759
Published: ICML 2016(Best Paper Award)
Affiliation: Google DeepMind
Highlights & Drawbacks
Fully tractable modeling of image distribution
PixelRNN & PixelC...
Generative Image Inpainting with Contextual Attention - Yu - CVPR 2018 - TensorFlow
Info
Title: Generative Image Inpainting with Contextual Attention
Task: Image Inpainting
Author: J. Yu, Z. Lin, J. Yang, X. Shen, X. Lu, and T. S. Huang
Date: Jan. 2018
Arxiv: 1801.07892
Published: CVPR 2018
Affiliation: UIUC & Adobe
Highlights & Drawbacks
A novel contextual attention layer to explicitly attend on re...
Generating Diverse High-Fidelity Images with VQ-VAE-2 - Razavi - 2019
Info
Title: Generating Diverse High-Fidelity Images with VQ-VAE-2
Task: Image Generation
Author: A. Razavi, A. van den Oord, and O. Vinyals
Date: Jun. 2019
Arxiv: 1906.00446
Affiliation: Google DeepMind
Highlights & Drawbacks
Diverse generated results
A multi-scale hierarchical organization of VQ-VAE
Self-attention mech...
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning - Nazeri - 2019 - PyTorch
Info
Title: EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
Task: Image Inpainting
Author: K. Nazeri, E. Ng, T. Joseph, F. Qureshi, and M. Ebrahimi
Date: Jan. 2019
Arxiv: 1901.00212
Published: ICCV 2019 Workshop
Highlights & Drawbacks
Interactive sketch editing for image completion
A two-stage adv...
Globally and locally consistent image completion - Iizuka - SIGGRAPH 2017
Info
Title: Globally and locally consistent image completion
Task: Image Inpainting
Author: S. Iizuka, E. Simo-Serra, and H. Ishikawa
Date: Jul. 2017
Published: SIGGRAPH 2017
Highlights & Drawbacks
A high performance network model that can complete arbitrary
missing regions
A globally and locally consistent adversarial tra...
(VQ-VAE)Neural Discrete Representation Learning - van den Oord - NIPS 2017 - TensorFlow & PyTorch Code
Info
Title: Neural Discrete Representation Learning
Task: Image Generation
Author: A. van den Oord, O. Vinyals, and K. Kavukcuoglu
Date: Nov. 2017
Arxiv: 1711.00937
Published: NIPS 2017
Affiliation: Google DeepMind
Highlights & Drawbacks
Discrete representation for data distribution
The prior is learned instead of rando...
CondenseNet: An Efficient DenseNet using Learned Group Convolutions - Huang - CVPR 2018
Info
Title: CondenseNet: An Efficient DenseNet using Learned Group Convolutions
Task: Image Classification
Author: Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger
Date: Nov. 2017
Arxiv: 1711.09224
Published: CVPR 2018
Highlights & Drawbacks
Learned manner for group hyper-params
Implementation with sta...
104 post articles, 11 pages.