Adversarial Learning with Local Coordinate Coding

By Jiezhang Cao, Yong Guo, Qingyao Wu, Chunhua Shen, Junzhou Huang, Mingkui Tan. 2018

39 citations recorded by the source corpus.

Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data, which, however, is hard to be used for sampling in GANs. In this paper, rather than sampling from the pre-defined prior distribution, we propose a Local Coordinate Coding (LCC) based sampling method to improve GANs. We derive a generalization bound for LCC based GANs and prove that a small dimensional input is sufficient to achieve good generalization. Extensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Mingkui Tan
2. Yi Yang
3. Jian Chen
4. Yong Guo
5. Linchao Zhu
6. Chuang Gan
7. Ming-Hsuan Yang
8. Luc Van Gool

In Representation & Self-Supervised Learning

1. Wenbing Huang
2. Yong Guo
3. Chuang Gan
4. Peilin Zhao
5. Minfeng Zhu
6. Deng Huang
7. Qi Chen
8. Runhao Zeng

Citations in the corpus

• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (2019, background): “With the recent successes of Variational Autoencoders (VAEs) [9] and GANs [4], a large number of methods have been proposed to handle generation [14, 17, 28, 1] and domain adaptation task [25, 32].”
• Discrimination-aware Channel Pruning for Deep Neural Networks (2018, background): “, image classification [21, 41], face recognition [37, 42], object detection [34, 35], image generation [3, 7] and video analysis [38, 47].”
• Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation (2019, methodology): “Generative Adversarial Network(GAN) [13], lets generator G and discriminator D compete against each other, is widely applied because of its powerful ability for learning and generalizing from data distribution.”
• Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search (2020, methodology): “…the candidate subspace, CNAS performs much accurate architecture sampling, thus can significantly improve the search efficiency and find better architectures than standard NAS methods. et al., 2017; Chen et al., 2019; Zeng et al., 2019; Hosseini et al., 2020; Guo et al., 2020b; Cao et al., 2018).”
• Auto-Embedding Generative Adversarial Networks For High Resolution Image Synthesis (2019, background): “achieved great success and become the workhorse of many challenging tasks, including image generation [1], [23], [43] video prediction [19], [24] and image translation [10], [23], [51], [58].”
• Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution (2020, unknown): “Specifically, a cycle consistency loss is proposed to avoid the mode collapse issue of GAN methods [56, 4, 5] and help minimize the distribution divergence.”
• NAT: Neural Architecture Transformer for Accurate and Compact Architectures (2019, background): “…networks (DNNs) [25] have been producing state-of-the-art results in many challenging tasks including image classification [12, 23, 43, 60, 61, 18, 11, 56], face recognition [39, 44, 59], brain signal processing [34, 35], video analysis [48, 53, 52] and many other areas [58, 57, 24, 3, 10, 9, 4].”
• Location-Aware Graph Convolutional Networks for Video Question Answering (2020, background): “Recently, deep learning has witnessed a great process (Tan, Tsang, and Wang 2014; Cao et al. 2018; 2019; Gan et al. 2019; Guo et al. 2019a).”
• Discrimination-Aware Network Pruning for Deep Model Compression (2020, background): “, image classification [20], [35], [68], face recognition [9], [62], [69], object detection [43], [59], [60], image generation [5], [12], [14] and video analysis [64], [77], [84].”
• Dense Regression Network for Video Grounding (2020, background): “Recently, great progress has been achieved in deep learning [48, 47, 2, 15, 13, 14, 19, 1, 51], which facilitates the development of video grounding.”