OpenCodePapers

open-vocabulary-semantic-segmentation-on-pascal-context-59

Semantic SegmentationOpen Vocabulary Semantic Segmentation
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodemIoUModelNameReleaseDate
DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation64.7DiSa (CLIP ViT-L/14)2026-01-27
PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation✓ Link64.7PCA-Seg (ViT-L/14)2026-03-18
HyperSeg: Towards Universal Visual Segmentation with Large Language Model✓ Link64.6HyperSeg2024-11-26
dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv364.27dinov3.seg2026-03-19
DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction63.8DCP-CLIP (CLIP ViT-L/14)2026-03-14
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation63.7X-Agent (CLIP ViT-L/14)2025-09-01
SILC: Improving Vision Language Pretraining with Self-Distillation63.5SILC2023-10-20
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer63.5InfoCLIP (CLIP ViT-L/14)2025-11-20
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation✓ Link63.3CAT-Seg2023-03-21
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation✓ Link62.5MaskCLIP++2024-12-16
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction✓ Link62.3CLIPSelf2023-10-02
PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation✓ Link62.2PCA-Seg (ViT-B/16)2026-03-18
Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation62.0OVSNet2025-06-19
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding✓ Link61.0UMG-CLIP-L/142024-01-12
EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass60.9EOVSAM2026-08-03
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation✓ Link60.6SED2023-11-27
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation✓ Link60.4Mask-Adapter2024-12-05
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing✓ Link60.2EBSeg-L2024-06-14
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation✓ Link59.4MAFT+2024-08-01
Open-Vocabulary Segmentation with Semantic-Assisted Calibration✓ Link59.3SCAN2023-12-07
DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation59.3DiSa (CLIP ViT-B/16)2026-01-27
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation✓ Link58.5MAFT-ViTL2023-09-30
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP✓ Link58.4FC-CLIP2023-08-04
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer58.1InfoCLIP (CLIP ViT-B/16)2025-11-20
DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction58.1DCP-CLIP (CLIP ViT-B/16)2026-03-14
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation57.7X-Agent (CLIP ViT-B/16)2025-09-01
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models✓ Link57.3ODISE2023-03-08
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP✓ Link55.7OVSeg Swin-B2022-10-09
Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation✓ Link55.4OVRCOAT2026-03-22
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning✓ Link50.1PACL2022-12-09
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model✓ Link47.7SimSeg2021-12-29
Open-Vocabulary Universal Image Segmentation with MaskCLIP✓ Link45.9MaskCLIP2022-08-18
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification✓ Link37.6TaAlign(trained with image-text pairs)2023-12-21
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link37.4TTD (TCL)2024-03-30
In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation✓ Link34.7LaVG2024-08-09
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs✓ Link33.9TCL2022-12-01
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias✓ Link31.0TTD (MaskCLIP)2024-03-30
A Closer Look at the Explainability of Contrastive Language-Image Pre-training✓ Link29.3CLIP Surgery (original CLIP without any fine-tuning)2023-04-12