AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task

Maya Okawa, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 4 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
Increase concept distance of test class from training classesConditional diffusion model · Synthetic shapeslearning speed of compositional generalizationHurt
Measure compositional accuracy multiplicatively instead of additivelyClass 111 accuracy · Synthetic shapesaccuracy dynamicsMixed
Add a fourth concept variable (background color)Conditional diffusion model · Synthetic shapes, 4 concept variablesaccuracy by concept distanceNo clear effect
Increase samples of concept class 001 in training data from 0 to 300 (ablation)Conditional diffusion model · Synthetic shapes, class 001accuracy of color capability: approx. 10 samplesImproved
Increase samples of concept class 100 in training data from 0 to 300 (ablation)Conditional diffusion model · Synthetic shapes, class 100accuracy of shape capabilityImproved
Fine-tune on added nodes 101, 010, 011 after adversarial training (ablation)Conditional diffusion model · Adversarial taskgeneration of correct small circlesHurt
Train on non-neighboring concept classes (adversarial setup) (ablation)Conditional diffusion model · Adversarial taskcompositional generalizationHurt
Underrepresented gender class in CelebA training dataConditional diffusion model · CelebAconvergence speed of gender accuracyHurt

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