AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback

Xin Jin, Bohan Li, Baao Xie, Wenyao Zhang, Jinming Liu, Ziqiang Li, Tao Yang, Wenjun Zeng

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add beta-VAE distillation and diffusion feedback to Diff-AEDiff-AE · FFHQ, optical-flow disentanglement metricchanged/frozen ratio (lower is better): 0.1606 -> 0.0177Improved
add diffusion-feedback dynamic capacity C_dyn on top of knowledge distillation (ablation)CL-Dis · FFHQqualitative disentanglement (Hair direction)Improved
add knowledge distillation from beta-VAE latent (ablation)Diff-AE with navigation · FFHQqualitative disentanglementImproved
add semantic navigation only to Diff-AE latent (ablation)Diff-AE · FFHQqualitative generation quality and disentanglementMixed
narrow gap between C_max and C_base (ablation)CL-Dis · Cars3DFactorVAE score: 0.794 -> 0.762Hurt
set C_base to 10 instead of 2, 5 or 20 (ablation)CL-Dis · Cars3DFactorVAE score: 0.689 (C_base 2) -> 0.794 (C_base 10)Improved
reduce z_sem dimension from 512 to 32 (ablation)CL-Dis · Shapes3DFactorVAE score: 0.840 -> 0.837No clear effect
use CL-Dis semantic encoder instead of learning from scratch for face recognitionface recognition · VGGFace2accuracy (%): 81.82 -> 87.32 (5 epochs)Improved
use CL-Dis instead of VAE-based methods for generation qualityCelebA generation · CelebAFID: 132.80 -> 6.54Improved
apply CL-Dis to real-recorded MPI3D dataCL-Dis · MPI3Ddisentanglement scoreHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy