AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

VLSlice: Interactive Vision-and-Language Slice Discovery

Eric Slyman, Minsuk Kahng, Stefan Lee

ICCV 2023 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 7 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 VLSlice (clusters, similar/counterfactual refinement, correlation plot) instead of ListSortslice discovery interface · user study, both tasksimages cataloged: +84.58 images (p=0.017)Improved
use VLSlice instead of ListSortslice discovery interface · user study, both tasksnumber of slices: +0.5955 slices (p=0.295)No clear effect
use VLSlice instead of ListSortslice discovery interface · user study, both tasksslice coherency F1: +0.215 F1 (p=0.006)Improved
use VLSlice instead of ListSortslice discovery interface · user study, both tasksmissed images (representativeness): -2.1 missed (p=0.35)No clear effect
use VLSlice instead of ListSortslice discovery interface · House/Nice taskmissed images: 41 -> 70Hurt
use VLSlice instead of ListSortslice discovery interface · post-study Likert ratingsenjoyment / would use again: 5.27 -> 6.45 (enjoyed); 4.73 -> 6.45 (use again)Improved
use VLSlice instead of ListSortslice discovery interface · post-study Likert ratingsease of learning / ease of use: 6.27 -> 5.55 (learn); 6.00 -> 5.55 (use)Hurt
use VLSlice instead of ListSortslice discovery interface · Person/CEO slicesshare of slices on gender, skin tone, age: 34% -> 62%Improved
use VLSlice instead of ListSortslice discovery interface · House/Nice slicesshare of low-level color/structure/photographic slices: 45% -> 14%Improved
use change in augmented caption percentile instead of raw augmented caption similaritybias measure · extended captions (qualitative)effect of canonical imagesImproved

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