AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Identification of Systematic Errors of Image Classifiers on Rare Subgroups

Jan Hendrik Metzen, Robin Hutmacher, N. Grace Hua, Valentyn Boreiko, Dan Zhang

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 20 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
condition image synthesis on the subgroup prompt instead of an unconditional class prompt (ablation)PromptAttack · Car operational design domain (100 subgroups)subgroup coverage (95% CI bound on p(z)): CI upper bound less than 0.0001 (unconditional) -> CI lower bound greater than 0.005 (conditional)Improved
use Stable Diffusion v1.5 instead of v2-base or v2-1-base (ablation)PromptAttack · Zero-shot systematic error benchmarkrank of ground-truth subgroupImproved
increase samples per subgroup n_s to at least 16 (ablation)PromptAttack · Zero-shot systematic error benchmarkrank of ground-truth subgroupImproved
reduce diffusion inference steps to n_t=5 (ablation)PromptAttack · Zero-shot systematic error benchmarkrank of ground-truth subgroupNo clear effect
raise class prompt weight w_c from 1.0 to 1.5 (ablation)PromptAttack · Zero-shot systematic error benchmarkrank of ground-truth subgroupImproved
increase class prompt weight beyond 1.5 (ablation)PromptAttack · Zero-shot systematic error benchmarkrank of ground-truth subgroupHurt
use combinatorial testing with n_C=3 to test a subset of subgroupsPromptAttack vehicle experiment · ImageNet minivansubgroups tested: 1.230 of 18.720 subgroups exploredImproved
shift all semantic dimensions jointly rather than a single dimensionViT-B/16 on minivan prompts · ImageNet minivan to snowplowsamples misclassified as snowplow: 300 of 1000 samples misclassifiedImproved

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