AAAI 2022 accepted papers on Detection and segmentation
82 of the 1,319 papers accepted at AAAI 2022 (6.2%) are on Detection and segmentation, compared with 5.3% at AAAI 2021. They fall into 5 topics.
See AAAI 2022 in the interactive map
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 · 37 papers
- UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer (1,093 citations)
- Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (595 citations)
- Anchor DETR: Query Design for Transformer-Based Detector (484 citations)
- Shape-Adaptive Selection and Measurement for Oriented Object Detection (298 citations)
- I Can Find You! Boundary-Guided Separated Attention Network for Camouflaged Object Detection (249 citations)
- Edge-Aware Guidance Fusion Network for RGB–Thermal Scene Parsing (144 citations)
- Self-Supervised Pretraining for RGB-D Salient Object Detection (74 citations)
- Laneformer: Object-Aware Row-Column Transformers for Lane Detection (71 citations)
- Fully Attentional Network for Semantic Segmentation (62 citations)
- Active Boundary Loss for Semantic Segmentation (56 citations)
- CF-DETR: Coarse-to-Fine Transformers for End-to-End Object Detection (55 citations)
- Polygon-to-Polygon Distance Loss for Rotated Object Detection (43 citations)
and 25 more in the interactive map.
Open-set and few-shot detection · 22 papers
- Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment (208 citations)
- FrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations (130 citations)
- SCAN: Cross Domain Object Detection with Semantic Conditioned Adaptation (81 citations)
- You Only Infer Once: Cross-Modal Meta-Transfer for Referring Video Object Segmentation (47 citations)
- L-CoDe:Language-Based Colorization Using Color-Object Decoupled Conditions (41 citations)
- Improving Human-Object Interaction Detection via Phrase Learning and Label Composition (39 citations)
- Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics (38 citations)
- Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning (35 citations)
- A Causal Debiasing Framework for Unsupervised Salient Object Detection (34 citations)
- Close the Loop: A Unified Bottom-Up and Top-Down Paradigm for Joint Image Deraining and Segmentation (30 citations)
- A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications (27 citations)
- Retinomorphic Object Detection in Asynchronous Visual Streams (27 citations)
and 10 more in the interactive map.
Weakly supervised detection and segmentation · 12 papers
- Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation (134 citations)
- Rethinking Pseudo Labels for Semi-supervised Object Detection (95 citations)
- Uncertainty Estimation via Response Scaling for Pseudo-Mask Noise Mitigation in Weakly-Supervised Semantic Segmentation (82 citations)
- Reference-Guided Pseudo-Label Generation for Medical Semantic Segmentation (69 citations)
- Weakly-Supervised Salient Object Detection Using Point Supervision (56 citations)
- LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization (55 citations)
- SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal (53 citations)
- Semi-supervised Object Detection with Adaptive Class-Rebalancing Self-Training (52 citations)
- Exploring Visual Context for Weakly Supervised Person Search (39 citations)
- Label-Efficient Hybrid-Supervised Learning for Medical Image Segmentation (39 citations)
- Dual Decoupling Training for Semi-supervised Object Detection with Noise-Bypass Head (11 citations)
- Self-Supervised Object Localization with Joint Graph Partition (10 citations)
3D detection and driving · 8 papers
- Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection (151 citations)
- AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds (137 citations)
- Sparse Cross-Scale Attention Network for Efficient LiDAR Panoptic Segmentation (41 citations)
- Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving (30 citations)
- Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds (20 citations)
- Correlation Field for Boosting 3D Object Detection in Structured Scenes (8 citations)
- Stereo Neural Vernier Caliper (6 citations)
- Distribution Aware VoteNet for 3D Object Detection (4 citations)
Tracking · 3 papers
- Attribute-Based Progressive Fusion Network for RGBT Tracking (210 citations)
- One More Check: Making “Fake Background” Be Tracked Again (63 citations)
- Homography Decomposition Networks for Planar Object Tracking (21 citations)
