SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.06703 · ICCV · 2023

VLSlice: Interactive Vision-and-Language Slice Discovery

Stefan Lee, Eric Slyman, Minsuk Kahng

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent work in vision-and-language demonstrates that large-scale pretraining can learn generalizable models that are efficiently transferable to downstream tasks. While this may improve dataset-scale aggregate metrics, analyzing performance around hand-crafted subgroups targeting specific bias dimensions reveals systemic undesirable behaviors. However, this subgroup analysis is frequently stalled by annotation efforts, which require extensive time and resources to collect the necessary data. Prior art attempts to automatically discover subgroups to circumvent these constraints but typically leverages model behavior on existing task-specific annotations and rapidly degrades on more complex inputs beyond "tabular" data, none of which study vision-and-language models. This paper presents VLSlice, an interactive system enabling user-guided discovery of coherent representation-level subgroups with consistent visiolinguistic behavior, denoted as vision-and-language slices, from unlabeled image sets. We show that VLSlice enables users to quickly generate diverse high-coherency slices in a user study (n=22) and release the tool publicly 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.06703")
get_code_for_paper("2309.06703")
have("2309.06703")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2309.06703.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2309.06703.svg)](https://syntology.ai/paper/2309.06703)

Connect an agent — have() is free.