Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/EQUSS

EQUSS

Reported on 21 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical7 results

Semantic SegmentationonPotsdam-3
Accuracy· 2023-12-12
82
best: 83.3 (PriMaPs-EM+HP (DINO ViT-B/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Semantic SegmentationonCityscapes test
Accuracy· 2023-12-12
79.9
best: 84.3 (ViCE)
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Semantic SegmentationonCityscapes test
mIoU· 2023-12-12
22
best: 67.3 (EDANet)
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Semantic SegmentationonCOCO-Stuff-27
Clustering [Accuracy]· 2023-12-12
53.8
best: 81.1 (DynaSeg - FSF (ResNet-18 FPN))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Semantic SegmentationonCOCO-Stuff-27
Clustering [mIoU]· 2023-12-12
25.8
best: 54.1 (DynaSeg - FSF (ResNet-18 FPN))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Semantic SegmentationonCOCO-Stuff-27
Linear Classifier [Accuracy]· 2023-12-12
75.2
best: 77.3 (HCL (ViT-S/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Semantic SegmentationonCOCO-Stuff-27
Linear Classifier [mIoU]· 2023-12-12
41.2
best: 47.4 (HCL (ViT-S/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342

Computer Vision7 results

Unsupervised Semantic SegmentationonPotsdam-3
Accuracy· 2023-12-12
82
best: 83.3 (PriMaPs-EM+HP (DINO ViT-B/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Unsupervised Semantic SegmentationonCityscapes test
Accuracy· 2023-12-12
79.9
best: 84.3 (ViCE)
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Unsupervised Semantic SegmentationonCityscapes test
mIoU· 2023-12-12
22
best: 26.8 (CUPS)
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Unsupervised Semantic SegmentationonCOCO-Stuff-27
Clustering [Accuracy]· 2023-12-12
53.8
best: 81.1 (DynaSeg - FSF (ResNet-18 FPN))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Unsupervised Semantic SegmentationonCOCO-Stuff-27
Clustering [mIoU]· 2023-12-12
25.8
best: 54.1 (DynaSeg - FSF (ResNet-18 FPN))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Unsupervised Semantic SegmentationonCOCO-Stuff-27
Linear Classifier [Accuracy]· 2023-12-12
75.2
best: 77.3 (HCL (ViT-S/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
Unsupervised Semantic SegmentationonCOCO-Stuff-27
Linear Classifier [mIoU]· 2023-12-12
41.2
best: 47.4 (HCL (ViT-S/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342

Audio7 results

10-shot image generationonPotsdam-3
Accuracy· 2023-12-12
82
best: 83.3 (PriMaPs-EM+HP (DINO ViT-B/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
10-shot image generationonCityscapes test
Accuracy· 2023-12-12
79.9
best: 84.3 (ViCE)
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
10-shot image generationonCityscapes test
mIoU· 2023-12-12
22
best: 67.3 (EDANet)
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
10-shot image generationonCOCO-Stuff-27
Clustering [Accuracy]· 2023-12-12
53.8
best: 81.1 (DynaSeg - FSF (ResNet-18 FPN))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
10-shot image generationonCOCO-Stuff-27
Clustering [mIoU]· 2023-12-12
25.8
best: 54.1 (DynaSeg - FSF (ResNet-18 FPN))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
10-shot image generationonCOCO-Stuff-27
Linear Classifier [Accuracy]· 2023-12-12
75.2
best: 77.3 (HCL (ViT-S/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342
10-shot image generationonCOCO-Stuff-27
Linear Classifier [mIoU]· 2023-12-12
41.2
best: 47.4 (HCL (ViT-S/8))
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization arXiv:2312.07342