AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

MetaStreet: Semi-Supervised Multimodal Learning for Street-Level Socioeconomic Prediction

Meng Chen, Junjie Yang, Zechen Li, Kai Zhao, Hongjun Dai, Weiming Huang

ICML 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning

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
add the textual encoder to the visual-only variant (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
add the visual encoder to the text-only variant (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
add spatial adjacency matrix to the visual encoder (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
add pretrained category embeddings (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
add task-specific prompts to the LLM input (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
use Qwen LLM instead of BERT as text encoder (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
add geography-aware contrastive loss (ablation)MetaStreet · Wuhan and Xi'an street tasksACC / F1 / MRRImproved
increase negative sample size up to 64 (ablation)MetaStreet · Wuhan street function (10-class)ACC / F1 / MRRImproved
vary negative sample size 8 to 64 (ablation)MetaStreet · 4-class tasksACC / F1 / MRRNo clear effect
vary loss weight lambda (ablation)MetaStreet · Wuhan economic activity (4-class)ACC / F1 / MRRNo clear effect
use stronger contrastive weight (lambda 0.1) (ablation)MetaStreet · Xi'an house price (4-class)ACC / F1 / MRRImproved
use MetaStreet instead of the best competing baselineUSPM · Wuhan street function (10-class)ACC@1 (%): 47.01 -> 51.42Improved

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