# Semantic Segmentation on SWJTU-Vision-Language Source: [Semantic Segmentation on SWJTU-Vision-Language]() Collection index: [llms.txt]() Data updated: 2026-04-28T10:01:17.451Z Evaluation of Semantic Segmentation performance on the SWJTU-Vision-Language dataset, reporting Overall Accuracy (OA), Mean IoU (mIoU), and class-specific User's Accuracy scores. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Semantic Segmentation | | Dataset (including any stated split) | SWJTU-Vision-Language | | Metric | Overall Accuracy (OA) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Overall Accuracy (OA)](): Higher is better; unit: PERCENT. - [Mean IoU (mIoU)](): Higher is better; unit: PERCENT. - [User's Accuracy (Bare Ground)](): Higher is better; unit: PERCENT. - [User's Accuracy (Low Vegetation)](): Higher is better; unit: PERCENT. - [User's Accuracy (Trees)](): Higher is better; unit: PERCENT. - [User's Accuracy (Houses)](): Higher is better; unit: PERCENT. - [User's Accuracy (Water)](): Higher is better; unit: PERCENT. - [User's Accuracy (Roads)](): Higher is better; unit: PERCENT. - [User's Accuracy (Others)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Accuracy (OA) | Result date | Report paper | | --- | --- | --- | --- | | TSMNet | 69.73 | Not recorded | 69f03f6c55a3c32af89fa42e | | DenseCLIP | 68.09 | Not recorded | 69f03f6c55a3c32af89fa42e | | MSSNet | 65.68 | Not recorded | 69f03f6c55a3c32af89fa42e | | TACOSS | 65.43 | Not recorded | 69f03f6c55a3c32af89fa42e | | Deeplab v3+ | 65.34 | Not recorded | 69f03f6c55a3c32af89fa42e | | CMGFNet | 64.93 | Not recorded | 69f03f6c55a3c32af89fa42e | | DDHRNet | 62.63 | Not recorded | 69f03f6c55a3c32af89fa42e | | MCANet | 61.42 | Not recorded | 69f03f6c55a3c32af89fa42e | ### TSMNet Overall Accuracy (OA): 69.73. Result ID: 69f0853047f34ce924d6f8fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction. ### DenseCLIP Overall Accuracy (OA): 68.09. Result ID: 69f0853047f34ce924d6f8fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Multimodal","Supervision":"Text Supervision"}. This record does not assert independent reproduction. ### MSSNet Overall Accuracy (OA): 65.68. Result ID: 69f0853047f34ce924d6f8fa. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction. ### TACOSS Overall Accuracy (OA): 65.43. Result ID: 69f0853047f34ce924d6f8fc. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Multimodal","Supervision":"Text Supervision"}. This record does not assert independent reproduction. ### Deeplab v3+ Overall Accuracy (OA): 65.34. Result ID: 69f0853047f34ce924d6f8f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Single-modality"}. This record does not assert independent reproduction. ### CMGFNet Overall Accuracy (OA): 64.93. Result ID: 69f0853047f34ce924d6f8f7. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction. ### DDHRNet Overall Accuracy (OA): 62.63. Result ID: 69f0853047f34ce924d6f8f8. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction. ### MCANet Overall Accuracy (OA): 61.42. Result ID: 69f0853047f34ce924d6f8f9. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.