AI Paper Atlas

Research map / Benchmarks / Cityscapes val (single-scale)

Cityscapes val (single-scale) leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Cityscapes val (single-scale). Best mIoU: 84.09 (SENSE (Mask2Former), ICML 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Cityscapes val (single-scale) · mIoU

11 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
184.09SENSE (Mask2Former)
DINOv3-L/16
What Makes Synthetic Data Effective in Image Segmentation
ICML 2026 · Table 3
Fast diffusion sampling
282.6Multi-scale + cross-scale contrastive loss
UPerNet Swin-B
Multi-Scale and Cross-Scale Contrastive Learning for Semantic Segmentation
ECCV 2022 · Table 4a
CNN features
381.1Mask2Former w/ HPD3d3s
Mask2Former R50
HyPiDecoder: Hybrid Pixel Decoder for Efficient Segmentation and Detection
ICCV 2025 · Table 4
CNN features
481.1ISNet with ASPP as image-level module
ResNet-101
ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation
ICCV 2021 · Table 7
CNN features
580.8SegNeXt + FreqFusion
MSCAN-T
Frequency-Aware Feature Fusion for Dense Image Prediction
TPAMI 2024 · Table 4
Image restoration
680.4DGMN (full: DA+DW+DS)
ResNet-101
Dynamic Graph Message Passing Networks for Visual Recognition
TPAMI 2022 · Table 1
GNN architectures
780.12+SGPN-embed
Deeplab ResNet-38
Learning Propagation for Arbitrarily-Structured Data
ICCV 2019 · Table 3
Segmentation and detection
879.7NAT + BiSeNetNeural Architecture Transfer
TPAMI 2021 · Table 4
Neural architecture search
979.41+ ISDA
DeepLab-v3 ResNet-101
Regularizing Deep Networks with Semantic Data Augmentation
TPAMI 2021 · Table 7
Recognition and long-tail
1078.77FCN+MCIBI++
ResNet-50
MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation
TPAMI 2022 · Table 5
CNN features
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.