| Mask DINO (single scale) |
- PQ
- 59.5
- PQst
- -
- PQth
- -
|
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation 2022-06-06 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 |
| kMaX-DeepLab (single-scale) |
- PQ
- 58.5
- PQst
- 49.0
- PQth
- 64.8
|
kMaX-DeepLab: k-means Mask Transformer 2022-07-08 |
코드 1 · 코드 2 · 코드 3 |
| Mask2Former (Swin-L) |
- PQ
- 58.3
- PQst
- 48.1
- PQth
- 65.1
|
Masked-attention Mask Transformer for Universal Image Segmentation 2021-12-02 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 |
| Panoptic SegFormer (Swin-L) |
- PQ
- 56.2
- PQst
- 47.0
- PQth
- 62.3
|
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers 2021-09-08 |
코드 1 · 코드 2 · 코드 3 |
| Panoptic SegFormer (PVTv2-B5) |
- PQ
- 55.8
- PQst
- 46.5
- PQth
- 61.9
|
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers 2021-09-08 |
코드 1 · 코드 2 · 코드 3 |
| CMT-DeepLab (single-scale) |
- PQ
- 55.7
- PQst
- 46.8
- PQth
- 61.6
|
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation 2022-06-17 |
코드 1 · 코드 2 |
| K-Net (Swin-L) |
- PQ
- 55.2
- PQst
- 46.2
- PQth
- 61.2
|
K-Net: Towards Unified Image Segmentation 2021-06-28 |
코드 1 |
| MaskConver (ResNet50, single-scale) |
- PQ
- 53.6
- PQst
- 58.9
- PQth
- 45.6
|
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation 2023-12-11 |
코드 1 |
| MaskFormer (Swin-L) |
- PQ
- 53.3
- PQst
- 44.5
- PQth
- 59.1
|
Per-Pixel Classification is Not All You Need for Semantic Segmentation 2021-07-13 |
코드 1 · 코드 2 · 코드 3 |
| Panoptic FCN* (Swin-L) |
- PQ
- 52.7
- PQth
- 59.4
|
Fully Convolutional Networks for Panoptic Segmentation 2020-12-01 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 |
| REFINE (ResNeXt-101-DCN) |
- PQ
- 51.5
- PQst
- 39.2
- PQth
- 59.6
|
REFINE: Prediction Fusion Network for Panoptic Segmentation 2020-12-15 |
연결 없음 |
| MaX-DeepLab-L (single-scale) |
- PQ
- 51.3
- PQst
- 42.4
- PQth
- 57.2
|
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers 2020-12-01 |
코드 1 · 코드 2 · 코드 3 |
| Panoptic SegFormer (ResNet-101) |
- PQ
- 50.9
- PQst
- 43.0
- PQth
- 56.2
|
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers 2021-09-08 |
코드 1 · 코드 2 · 코드 3 |
| Panoptic SegFormer (ResNet-50) |
- PQ
- 50.2
- PQst
- 42.4
- PQth
- 55.3
|
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers 2021-09-08 |
코드 1 · 코드 2 · 코드 3 |
| DetectoRS (ResNeXt-101-64x4d, multi-scale) |
- PQ
- 50
- PQst
- 37.2
- PQth
- 58.5
|
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution 2020-06-03 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 |
| REFINE (ResNet-101-DCN) |
- PQ
- 49.6
- PQst
- 37.7
- PQth
- 57.5
|
REFINE: Prediction Fusion Network for Panoptic Segmentation 2020-12-15 |
연결 없음 |
| SpatialFlow(ResNet-101-FPN) |
- PQ
- 48.5
- PQst
- 37.9
- PQth
- 55.5
|
SpatialFlow: Bridging All Tasks for Panoptic Segmentation 2019-10-19 |
코드 1 |
| Ada-Segment (ResNet-101-DCN) |
- PQ
- 48.5
- PQst
- 37.6
- PQth
- 55.7
|
Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation 2020-12-07 |
연결 없음 |
| K-Net (R101-FPN-DCN) |
- PQ
- 48.3
- PQst
- 39.7
- PQth
- 54
|
K-Net: Towards Unified Image Segmentation 2021-06-28 |
코드 1 |
| SOGNet (ResNet-101-FPN) |
- PQ
- 47.8
|
SOGNet: Scene Overlap Graph Network for Panoptic Segmentation 2019-11-18 |
코드 1 |
| Panoptic FCN*++ (DCN-101-FPN) |
- PQ
- 47.5
- PQst
- 38.2
- PQth
- 53.7
|
Fully Convolutional Networks for Panoptic Segmentation 2020-12-01 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 |
| UPSNet (ResNet-101-FPN) |
- PQ
- 46.6
- PQst
- 36.7
- PQth
- 53.2
|
UPSNet: A Unified Panoptic Segmentation Network 2019-01-12 |
코드 1 |
| OCFusion (ResNeXt-101-FPN) |
- PQ
- 46.6
- PQst
- 35.7
- PQth
- 54.0
|
Learning Instance Occlusion for Panoptic Segmentation 2019-06-13 |
코드 1 |
| Panoptic-DeepLab (SWideRNet-[1, 1, 4], multi-scale) |
- PQ
- 46.5
- PQst
- 38.2
- PQth
- 52.0
|
Scaling Wide Residual Networks for Panoptic Segmentation 2020-11-23 |
연결 없음 |
| AUNet (ResNext-152-FPN) |
- PQ
- 46.5
- PQst
- 32.5
- PQth
- 55.8
|
Attention-guided Unified Network for Panoptic Segmentation 2018-12-10 |
연결 없음 |
| AUNet (ResNet-152-FPN) |
- PQ
- 45.5
- PQst
- 31.6
- PQth
- 54.7
|
Attention-guided Unified Network for Panoptic Segmentation 2018-12-10 |
연결 없음 |
| AUNet (ResNet-101-FPN) |
- PQ
- 45.2
- PQst
- 31.3
- PQth
- 54.4
|
Attention-guided Unified Network for Panoptic Segmentation 2018-12-10 |
연결 없음 |
| Axial-DeepLab-L (multi-scale) |
- PQ
- 44.2
- PQst
- 36.8
- PQth
- 49.2
|
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation 2020-03-17 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| Axial-DeepLab-L |
- PQ
- 43.6
- PQst
- 35.6
- PQth
- 48.9
|
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation 2020-03-17 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| AdaptIS (ResNeXt-101) |
- PQ
- 42.8
- PQst
- 31.8
- PQth
- 50.1
|
AdaptIS: Adaptive Instance Selection Network 2019-09-17 |
연결 없음 |