OpenCodePapers

open-vocabulary-semantic-segmentation-on-7

Open Vocabulary Semantic Segmentation
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodemIoUModelNameReleaseDate
SILC: Improving Vision Language Pretraining with Self-Distillation25.8SILC2023-10-20
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding✓ Link25.2UMG-CLIP-E/142024-01-12
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation✓ Link23.9MaskCLIP++2024-12-16
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation✓ Link23.8CAT-Seg2023-03-21
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding✓ Link23.2UMG-CLIP-L/142024-01-12
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation✓ Link22.7Mask-Adapter2024-12-05
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation✓ Link22.6SED2023-11-27
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation✓ Link21.6MAFT+2024-08-01
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing✓ Link21.0EBSeg-L2024-06-14
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP✓ Link18.2FC-CLIP2023-08-04
Open-Vocabulary Segmentation with Semantic-Assisted Calibration✓ Link16.7SCAN2023-12-07
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation✓ Link15.7MAFT-ViTL2023-09-30
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models✓ Link14.5ODISE2023-03-08
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP✓ Link12.4OVSeg Swin-B2022-10-09
Open-Vocabulary Universal Image Segmentation with MaskCLIP✓ Link10MaskCLIP2022-08-18
Check out how to contribute new results.