| Focal Attention for Long-Range Interactions in Vision Transformers | Dec 1, 2021 | image-classificationImage Classification | CodeCode Available | 1 |
| Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding | Nov 30, 2021 | 3D Classification3D Part Segmentation | CodeCode Available | 1 |
| PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images | Nov 30, 2021 | Graph Neural NetworkInstance Segmentation | CodeCode Available | 1 |
| CRIS: CLIP-Driven Referring Image Segmentation | Nov 30, 2021 | Contrastive LearningDecoder | CodeCode Available | 1 |
| The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration | Nov 30, 2021 | image-classificationImage Classification | CodeCode Available | 1 |
| DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation | Nov 29, 2021 | Domain AdaptationImage-to-Image Translation | CodeCode Available | 1 |
| Searching the Search Space of Vision Transformer | Nov 29, 2021 | Neural Architecture Searchobject-detection | CodeCode Available | 1 |
| End-to-End Referring Video Object Segmentation with Multimodal Transformers | Nov 29, 2021 | Inductive BiasInstance Segmentation | CodeCode Available | 1 |
| A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation | Nov 26, 2021 | Brain Tumor SegmentationDecoder | CodeCode Available | 1 |
| Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation | Nov 26, 2021 | Image SegmentationMedical Image Segmentation | CodeCode Available | 1 |
| Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning | Nov 26, 2021 | Contrastive LearningInstance Segmentation | CodeCode Available | 1 |
| Efficient Self-Ensemble for Semantic Segmentation | Nov 26, 2021 | SegmentationSemantic Segmentation | CodeCode Available | 1 |
| Mask Transfiner for High-Quality Instance Segmentation | Nov 26, 2021 | Instance SegmentationSegmentation | CodeCode Available | 1 |
| Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation | Nov 25, 2021 | Active LearningPrediction | CodeCode Available | 1 |
| NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition | Nov 25, 2021 | object-detectionObject Detection | CodeCode Available | 1 |
| Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations | Nov 25, 2021 | DecoderNovel View Synthesis | CodeCode Available | 1 |
| Semantic-Aware Generation for Self-Supervised Visual Representation Learning | Nov 25, 2021 | Representation LearningSemantic Segmentation | CodeCode Available | 1 |
| Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation | Nov 25, 2021 | PredictionSemantic Segmentation | CodeCode Available | 1 |
| BoxeR: Box-Attention for 2D and 3D Transformers | Nov 25, 2021 | 3D Object DetectionInstance Segmentation | CodeCode Available | 1 |
| Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes | Nov 24, 2021 | Anomaly DetectionAnomaly Segmentation | CodeCode Available | 1 |
| PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers | Nov 24, 2021 | Image Classificationobject-detection | CodeCode Available | 1 |
| Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling | Nov 24, 2021 | Instance SegmentationSemantic Segmentation | CodeCode Available | 1 |
| EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation | Nov 24, 2021 | Event-based Object SegmentationKnowledge Distillation | CodeCode Available | 1 |
| Conditional Object-Centric Learning from Video | Nov 24, 2021 | 3D geometryInstance Segmentation | CodeCode Available | 1 |
| SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning | Nov 24, 2021 | Contrastive LearningDomain Adaptation | CodeCode Available | 1 |
