AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes

Liu Liu, Alexandra Schild, Marco Cipriano, Fatimeh Al Ghannam, Freya Tan, Gerard de Melo, Andres Sevtsuk

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection

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
fine-tune Qwen2-VL-7B on pairwise social labels instead of zero-shotQwen2-VL-7B · Pairwise test setF1 (Yes): 0.53 -> 0.72Improved
use balanced data and drop Not Sure labels (ablation)Qwen2-VL-7B LoRA 64 · Pairwise test setF1 (Yes): 0.68 -> 0.72Improved
drop Not Sure labels on unbalanced data (ablation)Qwen2-VL-7B LoRA 64 · Pairwise test setF1 (Yes): 0.70 -> 0.68Hurt
increase data from 29k to 76k (ablation)Qwen2-VL-7B LoRA 64 · Pairwise test setF1 (Yes): 0.64 -> 0.70Improved
LoRA rank 128 instead of 64 on Qwen2.5-VL-7B (ablation)Qwen2.5-VL-7B · Pairwise test setF1 (No): 0.53 -> 0.39Hurt
use MINGLE pipeline vs zero-shot VLMsMINGLE · ELSAmIoU: 0.02 -> 0.64Improved
add distance and depth filtering of pairs (ablation)MINGLE · ELSAmIoU: 0.635 -> 0.634No clear effect
add distance filtering only (ablation)MINGLE · ELSAF1: 0.604 -> 0.608No clear effect

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