Dual Contradistinctive Generative Autoencoder

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 CVPR 2021 PDF CVPR 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation CelebA 128x128 DC-VAE FID 19.9 # 3
Image Generation CelebA-HQ 256x256 DC-VAE FID 15.81 # 12
Image Generation CIFAR-10 DC-VAE Inception score 8.2 # 55
FID 17.9 # 118
Image Generation LSUN Bedroom 128 x 128 DC-VAE FID 14.3 # 2
Image Generation STL-10 DC-VAE FID 41.9 # 21
Inception score 8.1 # 17

Methods