OpenCodePapers

open-vocabulary-semantic-segmentation-on-pascalvoc-20

Semantic SegmentationOpen Vocabulary Semantic Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodemIoUhIoUModelNameReleaseDate
DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation98.7DiSa2026-01-27
PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation✓ Link98.4PCA-Seg2026-03-18
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding✓ Link97.9UMG-CLIP-L/142024-01-12
dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv397.86dinov3.seg2026-03-19
SILC: Improving Vision Language Pretraining with Self-Distillation97.6SILC2023-10-20
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer97.5InfoCLIP (CLIP ViT-L/14)2025-11-20
DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction97.3DCP-CLIP (CLIP ViT-L/14)2026-03-14
Open-Vocabulary Segmentation with Semantic-Assisted Calibration✓ Link97.2SCAN2023-12-07
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation✓ Link97.0CAT-Seg2023-03-21
EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass97.0EOVSAM2026-08-03
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation✓ Link96.8MaskCLIP++2024-12-16
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation✓ Link96.5MAFT+2024-08-01
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing✓ Link96.4EBSeg-L2024-06-14
DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction95.9DCP-CLIP (CLIP ViT-B/16)2026-03-14
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer95.5InfoCLIP (CLIP ViT-B/16)2025-11-20
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP✓ Link95.4FC-CLIP2023-08-04
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP✓ Link94.5OVSeg Swin-B2022-10-09
Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation✓ Link94.1OVRCOAT2026-03-22
92.1MAFT-ViTL
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation✓ Link92.1MAFT-ViTL2023-09-30
HyperSeg: Towards Universal Visual Segmentation with Large Language Model✓ Link92.1HyperSeg2024-11-26
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition✓ Link89.484.4POMP2023-04-10
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification✓ Link87.9TagAlign(trained with image-text pairs)2023-12-21
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models✓ Link84.6ODISE2023-03-08
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs✓ Link83.2TCL2022-12-01
In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation✓ Link82.5LaVG2024-08-09
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning✓ Link72.3PACL2022-12-09
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model✓ Link77.5ZSSeg2021-12-29
Decoupling Zero-Shot Semantic Segmentation✓ Link73.3ZegFormer2021-12-15