Cityscapes
Canonical29papers using it
404HF downloads
4HF likes
2016first seen
Urban street scenes with fine pixel-level semantic segmentation across 30 classes, for driving perception.
Papers using Cityscapes (29)
- Golden Cudgel Network for Real-Time Semantic SegmentationPixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised SegmentationLUMA: Benchmarking Segmentation via a Lightweight Universal Mask AdapterDPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense PredictionNoisy Annotations in Semantic SegmentationFully Exploiting Vision Foundation Model's Profound Prior Knowledge for
Generalizable RGB-Depth Driving Scene ParsingA Turbo-Inference Strategy for Object Detection and Instance SegmentationBootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time AdaptationSENSE: Stereo OpEN Vocabulary SEmantic SegmentationSpatio-Temporal Attention for Consistent Video Semantic Segmentation in Automated DrivingAdapting Vision Transformers to Ultra-High Resolution Semantic Segmentation with Relay TokensSelective Masking based Self-Supervised Learning for Image Semantic SegmentationLearning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection DatasetsThe Missing Point in Vision Transformers for Universal Image SegmentationLeMoRe: Learn More Details for Lightweight Semantic SegmentationScene-Centric Unsupervised Panoptic SegmentationExploring Token-Level Augmentation in Vision Transformer for
Semi-Supervised Semantic SegmentationSemi-supervised Semantic Segmentation with Multi-Constraint Consistency
LearningPyramid Scene Parsing NetworkWeakly- and Semi-Supervised Panoptic SegmentationEnd-to-End Instance Segmentation with Recurrent AttentionPanoNet: Real-time Panoptic Segmentation through Position-Sensitive
Feature EmbeddingDecoder Denoising Pretraining for Semantic SegmentationBoundary-aware Instance SegmentationFeature Selective Transformer for Semantic Image SegmentationA Fully Convolutional Tri-branch Network (FCTN) for Domain AdaptationLow-Resolution Self-Attention for Semantic SegmentationPanSR: An Object-Centric Mask Transformer for Panoptic SegmentationSeamless Scene Segmentation