AI Paper Atlas

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

DocLayout-VL: A Foundational Model for Hierarchical, Open-set, and Promptable Document Layout Segmentation

Venkata Venna, Srihari Bandarupalli, Anirudh Srinivasan, R Raghuveer, Sai Madhusudan Gunda, SANTOSH RAVI KIRAN SARVADEVABHATLA

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 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
replace flat bbox-trained fine-tuned VLM with DocLayout-VL segmentation and hierarchy designQwen3-VL-8B · HOPLay-Docs-BenchOverall Score: 45.8 -> 79.4Improved
add Hierarchical Grounding Contextualizer (ablation)DocLayout-VL · HierLay-Docs-BenchOpen mIoU: 58.3 -> 77.5Improved
add SAM segmentation module and HGC to base VLM (ablation)Qwen3-VL-8B · HierLay-Docs-BenchOpen mIoU: 32.5 -> 77.5Improved
add structural loss L_struct (ablation)DocLayout-VL · HierLay-Docs-BenchOpen mIoU: 72.3 -> 77.5Improved
add background exclusion loss L_bg (ablation)DocLayout-VL · HierLay-Docs-BenchOpen mIoU: 69.2 -> 72.3Improved
use Qwen3-VL-8B backbone instead of InternVL3.5-8B (ablation)DocLayout-VL · HierLay-Docs-BenchOpen mIoU: 71.3 -> 77.5Improved
use three-stage curriculum instead of single joint fine-tuning (ablation)DocLayout-VL · HierLay-Docs-Bench (100% data)Open mIoU: 68.7 -> 77.5Improved
add HGC versus doubling data volume (ablation)DocLayout-VL · HierLay-Docs-BenchOpen mIoU: VLM+SAM 47.6 -> 53.1 with 25% -> 50% data; +HGC at 25% data 59.8Improved
scale VLM size within a family (Qwen3-VL-8B to 235B)zero-shot VLMs · HOPLay-Docs-BenchOverall Score: 31.6 -> 31.5No clear effect
zero-shot DocLayout-VL versus per-dataset trained detector on PubLayNetDocLayout-VL-8B-it · PubLayNetmAP@50:95: 96.9 (DocLayout-YOLO) vs 96.5No clear effect
zero-shot DocLayout-VL versus DocLayout-YOLO on label-rich benchmarkDocLayout-VL-8B-it · IndicDLPmAP@50:95: 54.5 -> 77.5Improved

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