| dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3 | | 42.19 | dinov3.seg | 2026-03-19 |
| PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation | ✓ Link | 41.5 | PCA-Seg (ViT-L/14) | 2026-03-18 |
| Reconstructing CLIP for Open-Vocabulary Dense Perception | | 41.5 | DenseRC (ViT-L/14) | 2026-06-03 |
| EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass | | 39.0 | EOVSAM | 2026-08-03 |
| DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation | | 38.9 | DiSa (CLIP ViT-L/14) | 2026-01-27 |
| SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features | ✓ Link | 38.8 | SigLIP 2 (L/16) + Cat-Seg | 2025-02-20 |
| HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space | | 38.7 | HyperCLIP++ (CLIP ViT-L/14) | 2026-09-21 |
| InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer | | 38.5 | InfoCLIP (CLIP ViT-L/14) | 2025-11-20 |
| UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding | ✓ Link | 38.2 | UMG-CLIP-E/14 | 2024-01-12 |
| Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation | ✓ Link | 38.2 | Mask-Adapter | 2024-12-05 |
| MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation | ✓ Link | 38.2 | MaskCLIP++ | 2024-12-16 |
| Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space | ✓ Link | 38.2 | HyperCLIP (ViT-L/14) | 2025-06-11 |
| Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation | | 38.2 | X-Agent (CLIP ViT-L/14) | 2025-09-01 |
| DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction | | 38.1 | DCP-CLIP (CLIP ViT-L/14) | 2026-03-14 |
| PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation | ✓ Link | 38.1 | PCA-Seg (ViT-B/16) | 2026-03-18 |
| CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation | ✓ Link | 37.9 | CAT-Seg | 2023-03-21 |
| SILC: Improving Vision Language Pretraining with Self-Distillation | | 37.7 | SILC | 2023-10-20 |
| UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding | ✓ Link | 36.1 | UMG-CLIP-L/14 | 2024-01-12 |
| Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation | ✓ Link | 36.1 | MAFT+ | 2024-08-01 |
| OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation | | 35.8 | OVSeg + OpenDAS | 2024-05-30 |
| SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation | ✓ Link | 35.2 | SED | 2023-11-27 |
| CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction | ✓ Link | 34.5 | CLIPSelf | 2023-10-02 |
| Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP | ✓ Link | 34.1 | FC-CLIP | 2023-08-04 |
| DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation | | 33.7 | DiSa (CLIP ViT-B/16) | 2026-01-27 |
| Open-Vocabulary Segmentation with Semantic-Assisted Calibration | ✓ Link | 33.5 | SCAN | 2023-12-07 |
| HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space | | 32.9 | HyperCLIP++ (CLIP ViT-B/16) | 2026-09-21 |
| Open-Vocabulary Semantic Segmentation with Image Embedding Balancing | ✓ Link | 32.8 | EBSeg-L | 2024-06-14 |
| DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction | | 32.4 | DCP-CLIP (CLIP ViT-B/16) | 2026-03-14 |
| Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation | | 32.1 | X-Agent (CLIP ViT-B/16) | 2025-09-01 |
| InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer | | 32.1 | InfoCLIP (CLIP ViT-B/16) | 2025-11-20 |
| Learning Mask-aware CLIP Representations for Zero-Shot Segmentation | ✓ Link | 32.0 | MAFT-ViTL | 2023-09-30 |
| Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning | ✓ Link | 31.4 | PACL | 2022-12-09 |
| Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models | ✓ Link | 29.9 | ODISE | 2023-03-08 |
| Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP | ✓ Link | 29.6 | OVSeg Swin-B | 2022-10-09 |
| Open-Vocabulary Universal Image Segmentation with MaskCLIP | ✓ Link | 23.7 | MaskCLIP | 2022-08-18 |
| | 20.7 | POMP | |
| A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model | ✓ Link | 20.5 | SimSeg | 2021-12-29 |
| TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias | ✓ Link | 17.0 | TTD (TCL) | 2024-03-30 |
| In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation | ✓ Link | 15.8 | LaVG | 2024-08-09 |
| TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias | ✓ Link | 12.7 | TTD (MaskCLIP) | 2024-03-30 |