| Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation | ✓ Link | 57.23% | Trans4PASS+ (multi-scale) | 2022-07-25 |
| Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation | ✓ Link | 56.45% | Trans4PASS+ (single-scale) | 2022-07-25 |
| Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation | ✓ Link | 56.38% | Trans4PASS (multi-scale) | 2022-03-02 |
| Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation | ✓ Link | 55.25% | Trans4PASS (single-scale) | 2022-03-02 |
| DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation | ✓ Link | 54.67% | DAFormer | 2021-11-29 |
| Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation | ✓ Link | 53.83% | PCS | 2021-03-31 |
| Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation | ✓ Link | 48.52% | P2PDA (Cityscapes+WildDash) | 2021-10-21 |
| Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation | ✓ Link | 44.58% | SIM | 2020-03-18 |
| MetaFormer Is Actually What You Need for Vision | ✓ Link | 43.18% | PoolFormer (MiT-B1) | 2021-11-22 |
| Capturing Omni-Range Context for Omnidirectional Segmentation | ✓ Link | 43.02% | ECANet | 2021-03-09 |
| Understanding The Robustness in Vision Transformers | ✓ Link | 42.54% | FAN (MiT-B1) | 2022-04-26 |
| SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | ✓ Link | 42.4% | SegFormer (MiT-B2) | 2021-05-31 |
| AS-MLP: An Axial Shifted MLP Architecture for Vision | ✓ Link | 42.05% | ASMLP (MiT-B1) | 2021-07-18 |
| Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation | ✓ Link | 41.99% | P2PDA (Cityscapes) | 2021-10-21 |
| CycleMLP: A MLP-like Architecture for Dense Prediction | ✓ Link | 40.16% | CycleMLP (MiT-B1) | 2021-07-21 |
| SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | ✓ Link | 38.5% | SegFormer (MiT-B1) | 2021-05-31 |
| DPT: Deformable Patch-based Transformer for Visual Recognition | ✓ Link | 36.50% | DPT (MiT-B1) | 2021-07-30 |
| Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers | ✓ Link | 35.7% | SETR (PUP, Transformer-L) | 2020-12-31 |
| Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers | ✓ Link | 35.6% | SETR (MLA, Transformer-L) | 2020-12-31 |
| Seamless Scene Segmentation | ✓ Link | 34.14% | Seamless (Mapillary) | 2019-05-03 |
| Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation | ✓ Link | 32.5% | DeepLabV3+ (ResNet-101) | 2018-02-07 |
| Disentangled Non-Local Neural Networks | ✓ Link | 32.1% | DNL (ResNet-101) | 2020-06-11 |
| ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data | ✓ Link | 32.04% | SwiftNet (Merge3) | 2020-08-20 |
| Confidence Regularized Self-Training | ✓ Link | 31.67% | CRST | 2019-08-26 |
| Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation | ✓ Link | 31.46% | CLAN | 2018-09-25 |
| Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions | ✓ Link | 31.20% | PVT (Tiny, FPN) | 2021-02-24 |
| Universal Semi-Supervised Semantic Segmentation | ✓ Link | 30.87% | USSS (Mapillary) | 2018-11-26 |
| Pyramid Scene Parsing Network | ✓ Link | 29.5% | PSPNet (ResNet-50) | 2016-12-04 |
| Panoptic Feature Pyramid Networks | ✓ Link | 28.8% | Semantic-FPN (ResNet-101) | 2019-01-08 |
| Dual Attention Network for Scene Segmentation | ✓ Link | 28.5% | DANet (ResNet-101) | 2018-09-09 |
| Universal Semi-Supervised Semantic Segmentation | ✓ Link | 26.98% | USSS (IDD) | 2018-11-26 |
| Real-time Semantic Segmentation with Fast Attention | ✓ Link | 26.9% | FANet (Resnet-34) | 2020-07-07 |
| In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images | ✓ Link | 25.67% | SwiftNet (Cityscapes) | 2019-03-20 |
| Fast-SCNN: Fast Semantic Segmentation Network | ✓ Link | 24.6% | Fast-SCNN | 2019-02-12 |
| DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing | ✓ Link | 23.66% | PASS | 2019-09-17 |
| ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation | ✓ Link | 16.65% | ERFNet | 2017-10-09 |