AI Paper Atlas

Research map / Benchmarks / VOC20

VOC20 leaderboard

18 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VOC20. Best mIoU: 98 (OpenWorldSAM, NeurIPS 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

VOC20 · mIoU

18 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
198OpenWorldSAM
SAM2 Hiera-Large + BEiT-3-Large
OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts
NeurIPS 2025 · Zero-shot performance table
CLIP and zero-shot
292.3ReME
CLIP ViT-B + DINOv2 ViT-L
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation
ICCV 2025 · Table 1
Open-set and few-shot detection
390CLIPer
CLIP ViT-L/14
CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
ICCV 2025 · Table 1
Open-set and few-shot detection
488.8CorrCLIP
CLIP ViT-B/16
CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation
ICCV 2025 · Table 1
Open-set and few-shot detection
588.7Trident
OpenCLIP ViT-H/14
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
ICCV 2025 · Table 2
Open-set and few-shot detection
687.1ClearCLIP + ResCLIP
ViT-B/16
ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
CVPR 2025 · Table 1
Human and embodied modeling
787RF-CLIP
CLIP ViT-B/16
Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
AAAI 2026 · Table 2
Open-set and few-shot detection
886.5OursTraining-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching
AAAI 2025 · Table 1
Open-set and few-shot detection
984.9DIH-CLIP
CLIP ViT-B/16
DIH-CLIP: Unleashing the Diversity of Multi-Head Self-Attention for Training-Free Open-Vocabulary Semantic Segmentation
ICCV 2025 · Table 1
CNN features
1084.5SFP
CLIP ViT-B/16
Feature Purification Matters: Suppressing Outlier Propagation for Training-Free Open-Vocabulary Semantic Segmentation
ICCV 2025 · Table 1
Open-set and few-shot detection
8 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.