Research map / Detection and segmentation / Open-set and few-shot detection
CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation
Dengke Zhang, Fagui Liu, Quan Tang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add scope reconstruction (SAM masks) (ablation) | ClearCLIP baseline · VOC21 | mIoU: 53.6 -> 68.1 | Improved |
| add value reconstruction (DINO similarity) (ablation) | ClearCLIP + SR · VOC21 | mIoU: 68.1 -> 68.5 | Improved |
| add map correction (ablation) | ClearCLIP + SR + VR · VOC21 | mIoU: 68.5 -> 72.5 | Improved |
| add feature refinement (ablation) | ClearCLIP + SR + VR + MC · VOC21 | mIoU: 72.5 -> 74.8 | Improved |
| add scope reconstruction (ablation) | SCLIP · VOC21 | mIoU: 59.6 -> 66.5 | Improved |
| add scope reconstruction (ablation) | ProxyCLIP · VOC21 | mIoU: 61.3 -> 67.0 | Improved |
| add scope reconstruction (ablation) | SC-CLIP · VOC21 | mIoU: 64.6 -> 66.0 | Improved |
| increase SR final mask size from 21x21 to 84x84 (ablation) | CorrCLIP SR · VOC21 | mIoU: 64.7 -> 70.2 | Improved |
| use DINO QK-QK similarity instead of CLIP Q-K (ablation) | CorrCLIP value reconstruction · VOC21 | mIoU: 69.5 -> 74.2 | Improved |
| use DINO QK-QK similarity instead of uniform similarity (ablation) | CorrCLIP value reconstruction · VOC21 | mIoU: 73.4 -> 74.2 | Improved |
| add mask merging (clustering) (ablation) | CorrCLIP · VOC21 | mIoU: 74.2 -> 74.8 | Improved |
| add semantic branch alone (no spatial branch) (ablation) | CorrCLIP · Cityscapes | mIoU: 48.3 -> 47.6 | Hurt |
Later papers that compared with this method
4 later accepted papers report CorrCLIP as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- CorrCLIPv2: Harnessing Unlabeled Images for Open-Vocabulary Semantic Segmentation (IJCV 2026 · better on 2 of 2 shared results)
- S2C2Seg: Semantic-Spatial Consistency and Category Optimization for Open-Vocabulary Segmentation (CVPR 2026 · better on 1 of 1 shared result)
- From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation (ECCV 2026 · better on 1 of 1 shared result)
- ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation (ICCV 2025 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ProxyCLIP — ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation (ECCV 2024) · better on 3 of 3 shared results
- ClearCLIP — ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Effective SAM Combination for Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels (NeurIPS 2024 · similarity 0.89)
- Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space (CVPR 2025 · similarity 0.89)
- Open-Vocabulary Segmentation with Semantic-Assisted Calibration (CVPR 2024 · similarity 0.89)
- CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- Open-Vocabulary Semantic Segmentation with Image Embedding Balancing (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
