Generative Cooperative Net for Image Generation and Data Augmentation

  title={Generative Cooperative Net for Image Generation and Data Augmentation},
  author={Qiangeng Xu and Zengchang Qin and Tao Wan},
How to build a good model for image generation given an abstract concept is a fundamental problem in computer vision. [] Key Result It is easy to set up and could help generate a very large synthesized dataset.

Generative modelling and adversarial learning

This thesis aims to both improve the quality of generative modelling and manipulate generated samples by specifying multiple scene properties and devise a novel model, called a perceptual adversarial network (PAN), which consists of two feed-forward convolutional neural networks: a transformation network and a discriminative network.

Recent Trends in Deep Generative Models: a Review

  • C. G. TurhanH. Ş. Bilge
  • Computer Science
    2018 3rd International Conference on Computer Science and Engineering (UBMK)
  • 2018
A comprehensive review ofGenerative models with defining relations among them is presented for a better understanding of GANs and AEs by pointing the importance of generative models.

Cropout: A General Mechanism for Reducing Overfitting on Convolutional Neural Networks

The proposed Cropout is able to enlarge the diversity of the feature-map produced by convolutional layer, and further improve the generalization ability of deep CNNs, and is applied to different modern deep networks to further boost the performance on image classification tasks.

Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation

Both qualitative and quantitative results show that the proposed generative model makes realistic signals and is very helpful for data augmentation and data analysis.

Amphibian Sounds Generating Network Based on Adversarial Learning

A generative network based on adversarial learning for synthesizing short-time audio streams and investigates the effectiveness of data augmentation for amphibian call sounds classification are proposed.

Group-Level Emotion Recognition Using a Unimodal Privacy-Safe Non-Individual Approach

This research investigated a frugal approach towards a model able to capture the global moods from the whole image without using face or pose detection, or any individual-based feature as input, and built a VGG-based model achieving 59.13% accuracy on the VGAF test set.

Boosting Text Classification Performance on Sexist Tweets by Text Augmentation and Text Generation Using a Combination of Knowledge Graphs

The approach improves sexist tweet classification significantly in the entire machine learning models and can be readily applied to any other small dataset size like hate speech or abusive language and text classification problem using any machine learning model.

Guess-It-Generator: Generating in a Lewis Signaling Framework through Logical Reasoning

The proposed model, Guess-It-Generator (GIG) is a collaborative framework that engages two recurrent neural networks in a guessing game of the kind first introduced by David Lewis in his famous work called the Lewis signaling game that is synonymous with the "20 Questions'' game.

Report: Dynamic Eye Movement Matching and Visualization Tool in Neuro Gesture

This work applies a method, "Time Warp Edit Distance", to calculate the similarity of their eye movement trajectories, and cluster eye movement pattern of audiences based on these pair-wised similarity metrics.


The author’s personal experiences, as well as those of other authors, are subject to copyright.



Generative Visual Manipulation on the Natural Image Manifold

This paper proposes to learn the natural image manifold directly from data using a generative adversarial neural network, and defines a class of image editing operations, and constrain their output to lie on that learned manifold at all times.

Context Encoders: Feature Learning by Inpainting

It is found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures, and can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.

Image-to-Image Translation with Conditional Adversarial Networks

Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.

Conditional Generative Adversarial Nets

The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.

Learning to generate chairs with convolutional neural networks

This work trains a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color and shows that the network can be used to find correspondences between different chairs from the dataset, outperforming existing approaches on this task.

Caffe: Convolutional Architecture for Fast Feature Embedding

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.