Multi-domain Multi-task Learning

Feel free to contact me or contribute if you find any interesting paper is missing!

Multi-task Learning

• X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks (ECCV, 2022) [paper] [code]

• X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation (ECCV, 2022) [paper]

• The Missing Link: Finding label relations across datasets (ECCV, 2022) [paper]

• OMNIVORE: A Single Model for Many Visual Modalities (CVPR, 2022) [paper] [code]

• Multi-Task Self-Training for Learning General Representations (ICCV, 2021) [paper]

• UniT: Multimodal Multitask Learning with a Unified Transformer (arXiv, 2021) [paper] [code]

Transfer Learning

• Transferability Metrics for Selecting Source Model Ensembles (CVPR 2022) [paper]

• Factors of influence for transfer learning across diverse appearance domains and task types (TPAMI, 2022) [paper]

Single-task Learning

Challenge

• Robust Vision Challenge (ECCV Workshop 2018, 2020, 2022)

• Adverse Conditions Dataset with Correspondences (ACDC) (ICCV 2021) [paper]

Image Classification

• [Meta-dataset] Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (ICLR, 2020) [paper] [dataset]

• [Visual Domain Decathlon] Learning multiple visual domains with residual adapters (NeurIPS, 2017) [paper] [dataset]

Dense Prediction Tasks & Object Detection

2022

• Learning Semantic Segmentation from Multiple Datasets with Label Shifts (ECCV, 2022) [paper] [code]

• Simple Multi-dataset Detection (CVPR, 2022) [paper] [code]

• Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding (CVPR, 2022) [paper]

• FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation (CVPR, 2022) [paper] [code]

• Multiple Adverse Weather Conditions Adaptation for Object Detection via Causal Intervention (TPAMI, 2022) [paper]

• Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (AAAI, 2022) [paper] [code]

• Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation (arXiv, 2022) [paper]

• Multi-Task, Multi-Domain Deep Segmentation with Shared Representations and Contrastive Regularization for Sparse Pediatric Datasets (arXiv, 2022) [paper]

2021

• Domain Adaptive Knowledge Distillation for Driving Scene Semantic Segmentation (WACV Workshop, 2021) [paper]

• Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey (arXiv, 2021) [paper]

• Geometric Unsupervised Domain Adaptation for Semantic Segmentation (ICCV, 2021) [paper]

• Multi-Domain Conditional Image Translation: Translating Driving Datasets from Clear-Weather to Adverse Conditions (ICCV Workshop, 2021) [paper]

• Multi-weather city: Adverse weather stacking for autonomous driving (ICCV workshop, 2021) [paper]

• DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation (CVPR, 2021) [paper] [code]

• DRIV100: In-The-Wild Multi-Domain Dataset and Evaluation for Real-World Domain Adaptation of Semantic Segmentation (arXiv, 2021) [paper]

• [MSeg] MSeg: A Composite Dataset for Multi-domain Semantic Segmentation (arXiv, 2021) (CVPR, 2020) [arXiv] [CVF] [code]

• [Multi-head] Multi-Domain Semantic-Segmentation using Multi-Head Model (ITSC, 2021) [paper]

• Semantic Segmentation on Multiple Visual Domains (arXiv, 2021) [paper]

2020 and Before

• [BDD100K] BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning (CVPR, 2020) [paper]

• Semantic Segmentation with Unsupervised Domain Adaptation Under Varying Weather Conditions for Autonomous Vehicles (Robotics and Automation Letters, 2020) [paper]

• Object Detection with a Unified Label Space from Multiple Datasets (ECCV, 2020) [paper]

• IDDA: a large-scale multi-domain dataset for autonomous driving (Robotics and Automation Letters, 2020) [paper] [dataset]

• Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer (TPAMI, 2020) [paper]

• Towards Universal Object Detection by Domain Attention (CVPR, 2019) [paper] [code]

• Robust Semantic Segmentation in Adverse Weather Conditions by means of Sensor Data Fusion (arXiv, 2019) [paper]

• Bridging the Day and Night Domain Gap for Semantic Segmentation (Symposium on Intelligent Vehicle, 2019) [paper]

• Don’t Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation (arXiv, 2019) [paper]

• Semantic Segmentation via Multi-task, Multi-domain Learning (S+SSPR, 2016) [paper]