AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models

Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 6 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
use latent diffusion (VQ/KL) instead of image-space DDIM (ablation)DisDiff · Shapes3DDCI / FactorVAE scoreImproved
remove invariant loss L_in from disentangling loss (ablation)DisDiff-VQ · Shapes3DdisentanglementHurt
remove variant loss L_va from disentangling loss (ablation)DisDiff-VQ · Shapes3DdisentanglementHurt
optimize disentangling loss on both decoder and encoder (ablation)DisDiff · Shapes3DdisentanglementHurt
use constant or loss weighting instead of encoder-difference weighting (ablation)DisDiff · Shapes3DdisentanglementHurt
use cross-attention instead of AdaGN for condition injection (ablation)DisDiff · Shapes3DdisentanglementHurt
remove orthogonal positional embedding or use learnable embedding (ablation)DisDiff · Shapes3DdisentanglementHurt
latent number greater than number of ground-truth factors (ablation)DisDiff · Shapes3DdisentanglementNo clear effect
reduce latent number to 3 (fewer than 6 factors)DisDiff · Shapes3DDCI: 0.723 -> 0.3279Hurt
DisDiff vs DisCo on MPI3DDisDiff-VQ · MPI3DFactorVAE score: 0.371 -> 0.617Improved
DisDiff vs DisCo on Cars3D DCIDisDiff-VQ · Cars3DDCI: 0.271 -> 0.232Hurt
DisDiff vs InfoDiffusion on CelebADisDiff · CelebATAD: 0.299 -> 0.3054Improved

Later papers that compared with this method

3 later accepted papers report DisDiff as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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