AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Show Me Examples: Inferring Visual Concepts from Image Sets

Nick Stracke, Kolja Bauer, Stefan Andreas Baumann, Miguel Angel Bautista, Joshua Susskind, Bjorn Ommer

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 0 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 context set from 2 to 4 images (ablation)Ours · ImageNet hierarchy (animal subtree)accuracy per instantiation (%): 54.60 -> 60.21Improved
increase context set from 4 to 7 images (ablation)Ours · ImageNet hierarchy (animal subtree)accuracy per instantiation (%): 60.21 -> 60.87No clear effect
increase context set from 2 to 4 images (ablation)Ours · ImageNet hierarchy (animal subtree)diversity: 0.780 -> 0.887Improved
replace 1 of 5 context images with random (ablation)Ours · ImageNet hierarchy (animal subtree)accuracy per instantiation (%): 60.21 -> 51.72Hurt
replace 2 of 5 context images with random (ablation)Ours · ImageNet hierarchy (animal subtree)accuracy per instantiation (%): 60.21 -> 39.81Hurt
replace 2 of 5 context images with random (ablation)Ours · ImageNet hierarchy (animal subtree)diversity: 0.875 -> 0.943No clear effect
use proposed Set Learner model instead of Visual PromptingVisual Prompting · ImageNet hierarchy (animal subtree)accuracy per concept (%): 39.16 -> 55.68Improved
use proposed model instead of ILLUME+ 3BILLUME+ 3B · ImageNet hierarchy (animal subtree)accuracy per concept (%): 37.15 -> 55.68Improved
use sketch queriesOurs vs Visual Prompting · Sketch queriesaccuracy per concept (%): 33.23 -> 39.53Improved
use sketch context and sketch queriesOurs vs Visual Prompting · Sketch context+queriesaccuracy per instantiation (%): 51.96 -> 50.37Hurt
use unseen ImageNet21k classes as contextOurs vs Visual Prompting · ImageNet21k unseen-class contextaccuracy per concept (%): 35.91 -> 47.62Improved
use ILLUME+ prompt 2 instead of prompt 3 (ablation)ILLUME+ · ImageNet hierarchyaccuracy per concept (%): 33.19 -> 37.15Improved

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