AI Paper Atlas

Research map / Benchmarks / COCO-Stuff

COCO-Stuff leaderboard

111 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on COCO-Stuff. Best mIoU: 59.5 (Ours, NeurIPS 2024).

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.

COCO-Stuff · mIoU

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

#mIoU ↑MethodPaperTopic
159.5Ours
DINOv2-ViT-B14-REG
Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure
NeurIPS 2024 · Table 2
Open-set and few-shot detection
257.7DP-SIMS
ConvNeXt-L
Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
CVPR 2024 · Table 1
Autoregressive and latent generation
352.9Neural Layout (LUMEN, 20 PCA)
ControlNet + SD1.5
Label-free Neural Semantic Image Synthesis
ECCV 2024 · Table 2
Text-to-image diffusion
452.2DenseMLLM
DenseMLLM-4B
DenseMLLM: Standard Multimodal LLMs for Dense Prediction
ICML 2026 · Table 1
Multimodal LLMs
551.34CA+SACSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen
AAAI 2024 · Table: ablation study of CA-tr
Open-set and few-shot detection
650.5UPerNet+IDRNet
Swin-Large
IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
NeurIPS 2023 · Table SOTA
CNN features
749LT-NetLayoutTransformer: Scene Layout Generation With Conceptual and Spatial Diversity
CVPR 2021 · Table 2
Open-set and few-shot detection
847.9ECGAN++Edge Guided GANs With Multi-Scale Contrastive Learning for Semantic Image Synthesis
TPAMI 2023 · Table 3
GANs
947.6Mask2Former + Swin-S (real + synthetic)
Swin-S
FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
NeurIPS 2023 · Table: joint training on COCO-
Open-set and few-shot detection
1046.7SegFormer-B5
MiT-B5
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
NeurIPS 2021 · Table: Ablation studies relate
CNN features
76 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

COCO-Stuff · FID

25 papers, each with its best reported number for its own method; lower is better.

15 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

COCO-Stuff · mIoU (val)

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

7 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.