ICLR 2021 Submission: Deeper VAEs Excel on Natural Image Benchmarks | Synced

ICLR 2021 submitted paper proposes efficient VAEs that outperform PixelCNN-based autoregressive models in log-likelihood on natural image benchmarks.

By · · 1 min read

Source: Synced | AI Technology & Industry Review

ICLR 2021 submitted paper proposes efficient VAEs that outperform PixelCNN-based autoregressive models in log-likelihood on natural image benchmarks.