paper-with-me

홈 › Papers

Dual Contradistinctive Generative Autoencoder

2020-11-19 · CVPR 2021 1 · Gaurav Parmar, Dacheng Li, Kwonjoon Lee, Zhuowen Tu

We present a new generative autoencoder model with dual contradistinctive losses to improve generative autoencoder that performs simultaneous inference (reconstruction) and synthesis (sampling). Our model, named dual contradistinctive generative autoencoder (DC-VAE), integrates an instance-level discriminative loss (maintaining the instance-level fidelity for the reconstruction/synthesis) with a set-level adversarial loss (encouraging the set-level fidelity for there construction/synthesis), both being contradistinctive. Extensive experimental results by DC-VAE across different resolutions including 32x32, 64x64, 128x128, and 512x512 are reported. The two contradistinctive losses in VAE work harmoniously in DC-VAE leading to a significant qualitative and quantitative performance enhancement over the baseline VAEs without architectural changes. State-of-the-art or competitive results among generative autoencoders for image reconstruction, image synthesis, image interpolation, and representation learning are observed. DC-VAE is a general-purpose VAE model, applicable to a wide variety of downstream tasks in computer vision and machine learning.

📄 PDF Abstract BibTeX arXiv:2011.10063

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationImage ReconstructionRepresentation Learning

Methods 이 논문이 사용한 방법론

USD Coin Customer Service Number +1-833-534-1729 설명 없음
Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

A Primal-Dual link between GANs and Autoencoders

2019-12-01 · NeurIPS 2019 12 · Hisham Husain, Richard Nock, Robert C. Williamson

Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence. The impressive, yet elusive empirical …

Generalization Bounds

Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds

2019-02-03 · Hisham Husain, Richard Nock, Robert C. Williamson

Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence. The impressive, yet elusive empirical …

Generalization Bounds

Generative Autoencoding of Dropout Patterns

2023-10-03 · Shunta Maeda

We propose a generative model termed Deciphering Autoencoders. In this model, we assign a unique random dropout pattern to each data point in the training dataset and then train an autoencoder to reconstruct the correspo…

Generative Adversarial Stacked Autoencoders

2020-11-22 · Ariel Ruiz-Garcia, Ibrahim Almakky, Vasile Palade, Luke Hicks

Generative Adversarial Networks (GANs) have become predominant in image generation tasks. Their success is attributed to the training regime which employs two models: a generator G and discriminator D that compete in a m…

Image Generation

Generative Adversarial Stacked Autoencoders for Facial Pose Normalization and Emotion Recognition

2020-07-19 · Ariel Ruiz-Garcia, Vasile Palade, Mark Elshaw, Mariette Awad

In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees. We …

Emotion RecognitionFacial Emotion Recognition