Dual Contradistinctive Generative Autoencoder
This work provides an incremental improvement to existing VAE models, offering enhanced performance for researchers and practitioners working on image reconstruction, synthesis, interpolation, and representation learning tasks.
This paper introduces the Dual Contradistinctive Generative Autoencoder (DC-VAE), a new generative autoencoder model that enhances simultaneous inference and synthesis. By integrating instance-level discriminative and set-level adversarial contradistinctive losses, DC-VAE achieves significant qualitative and quantitative performance improvements over baseline VAEs across various image resolutions (32x32 to 512x512).
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.