NeurIPS 2022 accepted papers on Detection and segmentation
89 of the 2,901 papers accepted at NeurIPS 2022 (3.1%) are on Detection and segmentation, compared with 2.6% at NeurIPS 2021. They fall into 5 topics.
See NeurIPS 2022 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
Open-set and few-shot detection · 37 papers
- AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation (199 citations)
- Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection (69 citations)
- DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection (64 citations)
- Visual Prompting via Image Inpainting (50 citations)
- Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation (37 citations)
- RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection (29 citations)
- SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos (26 citations)
- Self-Supervised Visual Representation Learning with Semantic Grouping (25 citations)
- Mask Matching Transformer for Few-Shot Segmentation (20 citations)
- Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos (20 citations)
- xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery (17 citations)
- Breaking Bad: A Dataset for Geometric Fracture and Reassembly (16 citations)
and 25 more in the interactive map.
CNN features · 32 papers
- SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation (488 citations)
- Focal Modulation Networks (146 citations)
- Class-Aware Adversarial Transformers for Medical Image Segmentation (78 citations)
- RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer (76 citations)
- SegViT: Semantic Segmentation with Plain Vision Transformers (76 citations)
- GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models (61 citations)
- Decoupling Features in Hierarchical Propagation for Video Object Segmentation (51 citations)
- A Unified Sequence Interface for Vision Tasks (49 citations)
- VITA: Video Instance Segmentation via Object Token Association (39 citations)
- Deep Fourier Up-Sampling (28 citations)
- Feature-Proxy Transformer for Few-Shot Segmentation (26 citations)
- SAPA: Similarity-Aware Point Affiliation for Feature Upsampling (25 citations)
and 20 more in the interactive map.
3D detection and driving · 10 papers
- DeepInteraction: 3D Object Detection via Modality Interaction (63 citations)
- Fully Sparse 3D Object Detection (40 citations)
- CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds (37 citations)
- Towards Efficient 3D Object Detection with Knowledge Distillation (28 citations)
- Spatial Pruned Sparse Convolution for Efficient 3D Object Detection (19 citations)
- MultiScan: Scalable RGBD scanning for 3D environments with articulated objects (6 citations)
- Unsupervised Adaptation from Repeated Traversals for Autonomous Driving (5 citations)
- MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation (4 citations)
- K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions
- Unifying Voxel-based Representation with Transformer for 3D Object Detection
Weakly supervised detection and segmentation · 6 papers
- Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation (25 citations)
- DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection (13 citations)
- What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs (9 citations)
- ComGAN: Unsupervised Disentanglement and Segmentation via Image Composition (2 citations)
- Semi-Supervised Video Salient Object Detection Based on Uncertainty-Guided Pseudo Labels (2 citations)
- [Re] Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
Tracking · 4 papers
- TAP-Vid: A Benchmark for Tracking Any Point in a Video (30 citations)
- Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking? (22 citations)
- Learning Graph-embedded Key-event Back-tracing for Object Tracking in Event Clouds (4 citations)
- [Re] Transparent Object Tracking Benchmark
