AAAI 2023 accepted papers on Detection and segmentation
100 of the 2,023 papers accepted at AAAI 2023 (4.9%) are on Detection and segmentation, compared with 6.2% at AAAI 2022. They fall into 5 topics.
See AAAI 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 · 34 papers
- Few-Shot Object Detection via Variational Feature Aggregation (139 citations)
- Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection (75 citations)
- Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning (60 citations)
- Adversarial Alignment for Source Free Object Detection (45 citations)
- Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from a Conditional Causal Perspective (43 citations)
- End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation (42 citations)
- Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation (32 citations)
- Bugs in the Data: How ImageNet Misrepresents Biodiversity (29 citations)
- Attention-Conditioned Augmentations for Self-Supervised Anomaly Detection and Localization (20 citations)
- COSMOS: Catching Out-of-Context Image Misuse Using Self-Supervised Learning (20 citations)
- Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation (16 citations)
- Amodal Instance Segmentation via Prior-Guided Expansion (15 citations)
and 22 more in the interactive map.
CNN features · 34 papers
- High-Resolution Iterative Feedback Network for Camouflaged Object Detection (213 citations)
- DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer (118 citations)
- PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers (115 citations)
- YOLOV: Making Still Image Object Detectors Great at Video Object Detection (86 citations)
- SARAS-Net: Scale and Relation Aware Siamese Network for Change Detection (77 citations)
- FeedFormer: Revisiting Transformer Decoder for Efficient Semantic Segmentation (59 citations)
- Real-World Deep Local Motion Deblurring (33 citations)
- Symmetry-Aware Transformer-Based Mirror Detection (33 citations)
- Memory-Aided Contrastive Consensus Learning for Co-salient Object Detection (32 citations)
- Efficient Mirror Detection via Multi-Level Heterogeneous Learning (30 citations)
- Learning Context-Aware Classifier for Semantic Segmentation (30 citations)
- HG-SL: Jointly Learning of Global and Local User Spreading Behavior for Fake News Early Detection (29 citations)
and 22 more in the interactive map.
Weakly supervised detection and segmentation · 16 papers
- Weakly-Supervised Camouflaged Object Detection with Scribble Annotations (118 citations)
- Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation (76 citations)
- Background-Mixed Augmentation for Weakly Supervised Change Detection (34 citations)
- Semantic-Aware Superpixel for Weakly Supervised Semantic Segmentation (32 citations)
- Weakly-Supervised Semantic Segmentation for Histopathology Images Based on Dataset Synthesis and Feature Consistency Constraint (28 citations)
- Point-Teaching: Weakly Semi-supervised Object Detection with Point Annotations (27 citations)
- ACL-Net: Semi-supervised Polyp Segmentation via Affinity Contrastive Learning (26 citations)
- Mind the Gap: Polishing Pseudo Labels for Accurate Semi-supervised Object Detection (25 citations)
- De-biased Teacher: Rethinking IoU Matching for Semi-supervised Object Detection (17 citations)
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (13 citations)
- Calibrated Teacher for Sparsely Annotated Object Detection (13 citations)
- Coarse2Fine: Local Consistency Aware Re-prediction for Weakly Supervised Object Localization (10 citations)
and 4 more in the interactive map.
3D detection and driving · 12 papers
- PolarFormer: Multi-Camera 3D Object Detection with Polar Transformer (191 citations)
- Transformation-Equivariant 3D Object Detection for Autonomous Driving (144 citations)
- Superpoint Transformer for 3D Scene Instance Segmentation (125 citations)
- CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer (122 citations)
- LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception (73 citations)
- RADIANT: Radar-Image Association Network for 3D Object Detection (46 citations)
- A Simple Baseline for Multi-Camera 3D Object Detection (26 citations)
- Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection (23 citations)
- StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-Based 3D Object Detection (15 citations)
- CLUE-AD: A Context-Based Method for Labeling Unobserved Entities in Autonomous Driving Data (5 citations)
- Language-Assisted 3D Feature Learning for Semantic Scene Understanding (4 citations)
- Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion (3 citations)
Tracking · 4 papers
- RGBD1K: A Large-Scale Dataset and Benchmark for RGB-D Object Tracking (59 citations)
- RSPT: Reconstruct Surroundings and Predict Trajectory for Generalizable Active Object Tracking (18 citations)
- Global Dilated Attention and Target Focusing Network for Robust Tracking (14 citations)
- Video Event Extraction via Tracking Visual States of Arguments (9 citations)