AI Paper Atlas

Research map / Benchmarks / CamVid

CamVid leaderboard

54 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CamVid. Best mIoU: 84.54 (HRNet + Contextrast++, TPAMI 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.

CamVid · mIoU

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

#mIoU ↑MethodPaperTopic
184.54HRNet + Contextrast++
HRNetV2-W48
Contextrast++: Robust Multi-Scale Contextual Contrastive Learning for Semantic Segmentation
TPAMI 2026 · Table 2
CNN features
284.33HRNet + Contextrast
HRNet
Contextrast: Contextual Contrastive Learning for Semantic Segmentation
CVPR 2024 · Table 2
CNN features
383.3MSeg
HRNet-V2-W48
MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation
CVPR 2020 · Zero-shot cross-dataset result
Open-set and few-shot detection
482.5RTFormer-BaseRTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
NeurIPS 2022 · Table 2
CNN features
582PIDNet-S-Wider
PIDNet-S
PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers
CVPR 2023 · Table: Comparison of speed and
CNN features
681.6Ours
DeepLabV3+ WideResNet38
Improving Semantic Segmentation via Efficient Self-Training
TPAMI 2021 · Table 6
Semi-supervised learning
780.5OCR + Ours
HRNetV2-W48
Cross-Image Pixel Contrasting for Semantic Segmentation
TPAMI 2024 · Table 7
CNN features
879.1GCNet-LGolden Cudgel Network for Real-Time Semantic Segmentation
CVPR 2025 · Table 4
CNN features
979.1HyperSeg-L
EfficientNet-B1
HyperSeg: Patch-Wise Hypernetwork for Real-Time Semantic Segmentation
CVPR 2021 · Table: CamVid results
CNN features
1079.1CCNet3D (T=5)
ResNet-101
CCNet: Criss-Cross Attention for Semantic Segmentation
ICCV 2019 · Table 9
CNN features
44 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.