NeurIPS 2021 accepted papers on Detection and segmentation
64 of the 2,508 papers accepted at NeurIPS 2021 (2.6%) are on Detection and segmentation, compared with 3.0% at NeurIPS 2020. They fall into 5 topics.
See NeurIPS 2021 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
CNN features · 25 papers
- SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (914 citations)
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (234 citations)
- XCiT: Cross-Covariance Image Transformers (231 citations)
- K-Net: Towards Unified Image Segmentation (197 citations)
- You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection (192 citations)
- Per-Pixel Classification is Not All You Need for Semantic Segmentation (166 citations)
- $\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression (145 citations)
- Focal Attention for Long-Range Interactions in Vision Transformers (75 citations)
- Intriguing Properties of Contrastive Losses (63 citations)
- SOLQ: Segmenting Objects by Learning Queries (57 citations)
- Dual-stream Network for Visual Recognition (35 citations)
- MST: Masked Self-Supervised Transformer for Visual Representation (29 citations)
and 13 more in the interactive map.
Open-set and few-shot detection · 25 papers
- LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation (161 citations)
- SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation (69 citations)
- Aligning Pretraining for Detection via Object-Level Contrastive Learning (53 citations)
- Mining the Benefits of Two-stage and One-stage HOI Detection (35 citations)
- Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations (34 citations)
- SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection (32 citations)
- Few-Shot Segmentation via Cycle-Consistent Transformer (31 citations)
- On Model Calibration for Long-Tailed Object Detection and Instance Segmentation (26 citations)
- Few-Shot Object Detection via Association and DIscrimination (24 citations)
- Large-Scale Unsupervised Object Discovery (24 citations)
- Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement (18 citations)
- Object-aware Contrastive Learning for Debiased Scene Representation (16 citations)
and 13 more in the interactive map.
Weakly supervised detection and segmentation · 6 papers
- SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving (32 citations)
- Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation (22 citations)
- Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection (18 citations)
- Looking Beyond Single Images for Contrastive Semantic Segmentation Learning (12 citations)
- COHESIV: Contrastive Object and Hand Embedding Segmentation In Video (9 citations)
- Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity (3 citations)
3D detection and driving · 5 papers
- One Million Scenes for Autonomous Driving: ONCE Dataset (131 citations)
- Object DGCNN: 3D Object Detection using Dynamic Graphs (50 citations)
- Progressive Coordinate Transforms for Monocular 3D Object Detection (49 citations)
- Revisiting 3D Object Detection From an Egocentric Perspective (9 citations)
- Trust, but Verify: Cross-Modality Fusion for HD Map Change Detection (3 citations)
