NeurIPS 2023 accepted papers on Detection and segmentation
107 of the 3,584 papers accepted at NeurIPS 2023 (3.0%) are on Detection and segmentation, compared with 3.1% at NeurIPS 2022. They fall into 5 topics.
See NeurIPS 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Open-set and few-shot detection · 60 papers
- Segment Everything Everywhere All at Once (151 citations)
- Segment Anything in High Quality (109 citations)
- SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model (49 citations)
- DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection (47 citations)
- Scaling Open-Vocabulary Object Detection (42 citations)
- OpenMask3D: Open-Vocabulary 3D Instance Segmentation (29 citations)
- Weakly Supervised 3D Open-vocabulary Segmentation (21 citations)
- Learning Mask-aware CLIP Representations for Zero-Shot Segmentation (13 citations)
- FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery (12 citations)
- Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition (12 citations)
- Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models (10 citations)
- Explain Any Concept: Segment Anything Meets Concept-Based Explanation (10 citations)
and 48 more in the interactive map.
CNN features · 21 papers
- Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism (261 citations)
- Rank-DETR for High Quality Object Detection (25 citations)
- Knowledge Diffusion for Distillation (23 citations)
- Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution (16 citations)
- IDRNet: Intervention-Driven Relation Network for Semantic Segmentation (14 citations)
- Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics (10 citations)
- Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union (10 citations)
- ClusterFomer: Clustering As A Universal Visual Learner (9 citations)
- Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation (7 citations)
- ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation (7 citations)
- Scattering Vision Transformer: Spectral Mixing Matters (7 citations)
- RevColV2: Exploring Disentangled Representations in Masked Image Modeling (6 citations)
and 9 more in the interactive map.
3D detection and driving · 13 papers
- MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues (14 citations)
- Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection (13 citations)
- Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion (11 citations)
- Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection (9 citations)
- CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection (8 citations)
- Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models (6 citations)
- STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection (4 citations)
- 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection (3 citations)
- RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection (3 citations)
- Depth-discriminative Metric Learning for Monocular 3D Object Detection (2 citations)
- HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception (2 citations)
- Query-based Temporal Fusion with Explicit Motion for 3D Object Detection (1 citation)
and 1 more in the interactive map.
Weakly supervised detection and segmentation · 9 papers
- Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping (64 citations)
- H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection (17 citations)
- DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model (10 citations)
- Active Learning for Semantic Segmentation with Multi-class Label Query (6 citations)
- Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection (6 citations)
- SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation (5 citations)
- HASSOD: Hierarchical Adaptive Self-Supervised Object Detection (4 citations)
- Weakly-Supervised Audio-Visual Segmentation (3 citations)
- Label-efficient Segmentation via Affinity Propagation
Tracking · 4 papers
- Type-to-Track: Retrieve Any Object via Prompt-based Tracking (9 citations)
- EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset (6 citations)
- Context-PIPs: Persistent Independent Particles Demands Spatial Context Features (5 citations)
- Reading Relevant Feature from Global Representation Memory for Visual Object Tracking (5 citations)