| dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3 | | 27.80 | dinov3.seg | 2026-03-19 |
| PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation | ✓ Link | 26.7 | PCA-Seg (ViT-L/14) | 2026-03-18 |
| SILC: Improving Vision Language Pretraining with Self-Distillation | | 25.8 | SILC | 2023-10-20 |
| UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding | ✓ Link | 25.2 | UMG-CLIP-E/14 | 2024-01-12 |
| DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation | | 24.9 | DiSa (CLIP ViT-L/14) | 2026-01-27 |
| InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer | | 24.6 | InfoCLIP (CLIP ViT-L/14) | 2025-11-20 |
| DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction | | 24.3 | DCP-CLIP (CLIP ViT-L/14) | 2026-03-14 |
| Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation | | 24.2 | X-Agent (CLIP ViT-L/14) | 2025-09-01 |
| MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation | ✓ Link | 23.9 | MaskCLIP++ | 2024-12-16 |
| CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation | ✓ Link | 23.8 | CAT-Seg | 2023-03-21 |
| UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding | ✓ Link | 23.2 | UMG-CLIP-L/14 | 2024-01-12 |
| Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation | ✓ Link | 22.7 | Mask-Adapter | 2024-12-05 |
| SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation | ✓ Link | 22.6 | SED | 2023-11-27 |
| PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation | ✓ Link | 22.3 | PCA-Seg (ViT-B/16) | 2026-03-18 |
| Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation | ✓ Link | 21.6 | MAFT+ | 2024-08-01 |
| Open-Vocabulary Semantic Segmentation with Image Embedding Balancing | ✓ Link | 21.0 | EBSeg-L | 2024-06-14 |
| EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass | | 20.4 | EOVSAM | 2026-08-03 |
| DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation | | 20.3 | DiSa (CLIP ViT-B/16) | 2026-01-27 |
| DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction | | 19.7 | DCP-CLIP (CLIP ViT-B/16) | 2026-03-14 |
| InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer | | 19.5 | InfoCLIP (CLIP ViT-B/16) | 2025-11-20 |
| Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation | | 19.2 | X-Agent (CLIP ViT-B/16) | 2025-09-01 |
| Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP | ✓ Link | 18.2 | FC-CLIP | 2023-08-04 |
| Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation | ✓ Link | 18.1 | OVRCOAT | 2026-03-22 |
| Open-Vocabulary Segmentation with Semantic-Assisted Calibration | ✓ Link | 16.7 | SCAN | 2023-12-07 |
| Learning Mask-aware CLIP Representations for Zero-Shot Segmentation | ✓ Link | 15.7 | MAFT-ViTL | 2023-09-30 |
| Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models | ✓ Link | 14.5 | ODISE | 2023-03-08 |
| Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP | ✓ Link | 12.4 | OVSeg Swin-B | 2022-10-09 |
| Open-Vocabulary Universal Image Segmentation with MaskCLIP | ✓ Link | 10 | MaskCLIP | 2022-08-18 |