| DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation | | 98.7 | | DiSa | 2026-01-27 |
| PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation | ✓ Link | 98.4 | | PCA-Seg | 2026-03-18 |
| UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding | ✓ Link | 97.9 | | UMG-CLIP-L/14 | 2024-01-12 |
| dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3 | | 97.86 | | dinov3.seg | 2026-03-19 |
| SILC: Improving Vision Language Pretraining with Self-Distillation | | 97.6 | | SILC | 2023-10-20 |
| InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer | | 97.5 | | InfoCLIP (CLIP ViT-L/14) | 2025-11-20 |
| DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction | | 97.3 | | DCP-CLIP (CLIP ViT-L/14) | 2026-03-14 |
| Open-Vocabulary Segmentation with Semantic-Assisted Calibration | ✓ Link | 97.2 | | SCAN | 2023-12-07 |
| CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation | ✓ Link | 97.0 | | CAT-Seg | 2023-03-21 |
| EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass | | 97.0 | | EOVSAM | 2026-08-03 |
| MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation | ✓ Link | 96.8 | | MaskCLIP++ | 2024-12-16 |
| Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation | ✓ Link | 96.5 | | MAFT+ | 2024-08-01 |
| Open-Vocabulary Semantic Segmentation with Image Embedding Balancing | ✓ Link | 96.4 | | EBSeg-L | 2024-06-14 |
| DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction | | 95.9 | | DCP-CLIP (CLIP ViT-B/16) | 2026-03-14 |
| InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer | | 95.5 | | InfoCLIP (CLIP ViT-B/16) | 2025-11-20 |
| Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP | ✓ Link | 95.4 | | FC-CLIP | 2023-08-04 |
| Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP | ✓ Link | 94.5 | | OVSeg Swin-B | 2022-10-09 |
| Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation | ✓ Link | 94.1 | | OVRCOAT | 2026-03-22 |
| | 92.1 | | MAFT-ViTL | |
| Learning Mask-aware CLIP Representations for Zero-Shot Segmentation | ✓ Link | 92.1 | | MAFT-ViTL | 2023-09-30 |
| HyperSeg: Towards Universal Visual Segmentation with Large Language Model | ✓ Link | 92.1 | | HyperSeg | 2024-11-26 |
| Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition | ✓ Link | 89.4 | 84.4 | POMP | 2023-04-10 |
| TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification | ✓ Link | 87.9 | | TagAlign(trained with image-text pairs) | 2023-12-21 |
| Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models | ✓ Link | 84.6 | | ODISE | 2023-03-08 |
| Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs | ✓ Link | 83.2 | | TCL | 2022-12-01 |
| In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation | ✓ Link | 82.5 | | LaVG | 2024-08-09 |
| Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning | ✓ Link | 72.3 | | PACL | 2022-12-09 |
| A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model | ✓ Link | | 77.5 | ZSSeg | 2021-12-29 |
| Decoupling Zero-Shot Semantic Segmentation | ✓ Link | | 73.3 | ZegFormer | 2021-12-15 |