Dual Contradistinctive Generative Autoencoder

By Gaurav Parmar, Dacheng Li, Kwonjoon Lee, Zhuowen Tu. 2020

94 citations recorded by the source corpus.

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 the reconstruction/synthesis), both being contradistinctive. Extensive experimental results by DC-VAE across different resolutions including 32×32, 64×64, 128×128, and 512×512 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.

Subfields: Computer Vision and Pattern Recognition, Generative Models

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

In Generative Models

Citations in the corpus

High-Resolution Image Synthesis with Latent Diffusion Models (2021, background): “CelebA-HQ results reproduced from [42, 61, 96], FFHQ from [41, 42].”
Score-based Generative Modeling in Latent Space (2021, background): “[77] Gaurav Parmar, Dacheng Li, Kwonjoon Lee, and Zhuowen Tu.”
On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation (2021, background): “A wide range of image and video synthesis applications [45, 54, 67, 83] have been enabled, as a result of tremendous progress in deep generative models such as GANs [9, 28, 34, 37, 59], VAEs [41, 55, 61], autoregressive models [52], flow-based models [18, 40], and energy-based models [21, 50, 63].”
On Aliased Resizing and Surprising Subtleties in GAN Evaluation (2022, background): “A wide range of image and video synthesis applications [41, 50, 61, 77] have been enabled, as a result of tremendous progress in deep generative models such as GANs [7, 24, 30, 33, 54], VAEs [37, 51, 56], autoregressive models [48], flow-based models [14, 36], and energy-based models [17, 46, 58].”
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs (2021, methodology): “LAE (Pidhorskyi et al., 2020) 19.2 VQ-GAN (Esser et al., 2021b) 10.2 DC-AE (Parmar et al., 2021) 15.8 Table 5: Generative results on LSUN Church 256 Model FID↓ Denoising Diffusion GAN (ours) 5.25 DDPM (Ho et al., 2020) 7.89 ImageBART (Esser et al., 2021a) 7.32 Gotta Go Fast (Jolicoeur-Martineau et a”
Dataset Condensation with Distribution Matching (2021, unknown): “More detailed comparison and discussion to other methods [40, 32, 33], MMD baseline [18] and generative baselines including DC-VAE [34], BigGAN [8] and GMMN [28] can be found in the appendix.”
Score Matching Model for Unbounded Data Score (2021, unknown): “16 Likelihood-based Models DC-VAE [29] 15.”