CVPR 2020 accepted papers on Detection and segmentation
243 of the 1,467 papers accepted at CVPR 2020 (16.6%) are on Detection and segmentation, compared with 18.5% at CVPR 2019. They fall into 5 topics.
See CVPR 2020 in the interactive map
Submitting to CVPR? 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 · 115 papers
- EfficientDet: Scalable and Efficient Object Detection (9,058 citations)
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks (8,780 citations)
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2,370 citations)
- PointRend: Image Segmentation As Rendering (1,175 citations)
- Multi-Scale Interactive Network for Salient Object Detection (861 citations)
- Multi-Scale Progressive Fusion Network for Single Image Deraining (788 citations)
- CenterMask: Real-Time Anchor-Free Instance Segmentation (724 citations)
- On the Detection of Digital Face Manipulation (722 citations)
- Rethinking Classification and Localization for Object Detection (718 citations)
- PolarMask: Single Shot Instance Segmentation With Polar Representation (676 citations)
- Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (631 citations)
- BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation (626 citations)
and 103 more in the interactive map.
Open-set and few-shot detection · 65 papers
- Camouflaged Object Detection (914 citations)
- Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings (914 citations)
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (638 citations)
- Equalization Loss for Long-Tailed Object Recognition (500 citations)
- Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery (342 citations)
- Exploring Categorical Regularization for Domain Adaptive Object Detection (337 citations)
- PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection (297 citations)
- Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax (283 citations)
- Advancing High Fidelity Identity Swapping for Forgery Detection (279 citations)
- Cross-Domain Detection via Graph-Induced Prototype Alignment (269 citations)
- Learning Human-Object Interaction Detection Using Interaction Points (258 citations)
- FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation (255 citations)
and 53 more in the interactive map.
Tracking · 25 papers
- Siamese Box Adaptive Network for Visual Tracking (1,015 citations)
- SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (947 citations)
- Learning a Neural Solver for Multiple Object Tracking (512 citations)
- Deformable Siamese Attention Networks for Visual Object Tracking (475 citations)
- AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization (422 citations)
- D3S - A Discriminative Single Shot Segmentation Tracker (312 citations)
- TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model (295 citations)
- RetinaTrack: Online Single Stage Joint Detection and Tracking (250 citations)
- GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning (243 citations)
- How to Train Your Deep Multi-Object Tracker (229 citations)
- Tracking by Instance Detection: A Meta-Learning Approach (190 citations)
- PnPNet: End-to-End Perception and Prediction With Tracking in the Loop (183 citations)
and 13 more in the interactive map.
3D detection and driving · 21 papers
- nuScenes: A Multimodal Dataset for Autonomous Driving (6,931 citations)
- Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather (610 citations)
- MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships (321 citations)
- Predicting Semantic Map Representations From Images Using Pyramid Occupancy Networks (260 citations)
- HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection (244 citations)
- DSGN: Deep Stereo Geometry Network for 3D Object Detection (224 citations)
- MLCVNet: Multi-Level Context VoteNet for 3D Object Detection (213 citations)
- Train in Germany, Test in the USA: Making 3D Object Detectors Generalize (171 citations)
- SESS: Self-Ensembling Semi-Supervised 3D Object Detection (142 citations)
- What You See is What You Get: Exploiting Visibility for 3D Object Detection (135 citations)
- Joint 3D Instance Segmentation and Object Detection for Autonomous Driving (117 citations)
- BidNet: Binocular Image Dehazing Without Explicit Disparity Estimation (77 citations)
and 9 more in the interactive map.
Weakly supervised detection and segmentation · 17 papers
- Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation (768 citations)
- Weakly-Supervised Salient Object Detection via Scribble Annotations (331 citations)
- Weakly-Supervised Semantic Segmentation via Sub-Category Exploration (319 citations)
- Single-Stage Semantic Segmentation From Image Labels (277 citations)
- Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection (220 citations)
- Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation (219 citations)
- Evaluating Weakly Supervised Object Localization Methods Right (191 citations)
- Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization (125 citations)
- Rethinking the Route Towards Weakly Supervised Object Localization (115 citations)
- Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks (103 citations)
- OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold (89 citations)
- SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection (82 citations)
and 5 more in the interactive map.
