# Transformer Scale Gate for Semantic Segmentation Source: [Transformer Scale Gate for Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:14:42.238Z Authors: Hengcan Shi, Munawar Hayat, Jianfei Cai Published: 2022-05-14T13:11:39.000Z ## Abstract Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales may degrade segmentation outcomes. Leveraging from the inherent properties of Vision Transformers, we propose a simple yet effective module, Transformer Scale Gate (TSG), to optimally combine multi-scale features.TSG exploits cues in self and cross attentions in Vision Transformers for the scale selection. TSG is a highly flexible plug-and-play module, and can easily be incorporated with any encoder-decoder-based hierarchical vision Transformer architecture. Extensive experiments on the Pascal Context and ADE20K datasets demonstrate that our feature selection strategy achieves consistent gains. ## Recorded benchmark results 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. - [Semantic Segmentation on PASCAL Context (val)](): Semantic segmentation; PASCAL Context (val); mIoU: 63.3. - [Semantic Segmentation on ADE20K (val)](): Semantic segmentation; ADE20K (val); mIoU: 54.2. - [Semantic Segmentation on Cityscapes (val)](): Semantic segmentation; Cityscapes (val); mIoU: not recorded. - [Semantic Segmentation on Pascal Context (test)](): Semantic segmentation; Pascal Context (test); mIoU: not recorded. ## Original sources and implementation [Original paper]() [PDF]()