No article text was recorded for this version.
shared-backbone multi-task learning
Version 1 of 142 papers44 conceptsfrozen 2026-10-04
Papers in this version
- Blog: RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
- Blog: Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
- Blog: FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction
- Blog: PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection
- Blog: Learning Local Feature Descriptor with Motion Attribute for Vision-based Localization
- Blog: Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
- Blog: YOLOP: You Only Look Once for Panoptic Driving Perception
- Blog: Learned Enrichment of Top-View Grid Maps Improves Object Detection
- Blog: Visual Multitask Real-Time Model in an Automatic Driving Scene
- Blog: Scene Understanding Networks for Autonomous Driving Based on Around View Monitoring System
- Blog: RadarGNN: Transformation Invariant Graph Neural Network for Radar-based Perception
- Blog: GarmNet: Improving Global with Local Perception for Robotic Laundry Folding
- Blog: Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point
- Blog: Language Adaptive Weight Generation for Multi-Task Visual Grounding
- Blog: Panoptic-PolarNet: Proposal-Free LiDAR Point Cloud Panoptic Segmentation
- Blog: SOGDet: Semantic-Occupancy Guided Multi-View 3D Object Detection
- Blog: ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Image
- Blog: Enhanced free space detection in multiple lanes based on single CNN with scene identification
- Blog: 3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
- Blog: Q-YOLOP: Quantization-aware You Only Look Once for Panoptic Driving Perception
- Blog: SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition
- Blog: Real-Time Semantic Stereo Matching
- Blog: MatchDet: A Collaborative Framework for Image Matching and Object Detection
- Blog: Multi-Task Learning-Enabled Automatic Vessel Draft Reading for Intelligent Maritime Surveillance
- Blog: SIUNet: Sparsity Invariant U-Net for Edge-Aware Depth Completion
- Blog: CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection
- Blog: DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
- Blog: S$^{3}$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving
- Blog: NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks
- Blog: RPRG: Toward Real-time Robotic Perception, Reasoning and Grasping with One Multi-task Convolutional Neural Network
- Blog: Raw High-Definition Radar for Multi-Task Learning
- Blog: BlitzNet: A Real-Time Deep Network for Scene Understanding
- Blog: 3D Domain Adaptive Instance Segmentation via Cyclic Segmentation GANs
- Blog: Multi-task Fusion for Efficient Panoptic-Part Segmentation
- Blog: DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization
- Blog: Autonomous Multitask Driving Systems Using Improved You Only Look Once Based on Panoptic Driving Perception
- Blog: Where and What: Driver Attention-based Object Detection
- Blog: Panoptic Feature Pyramid Networks
- Blog: Fully Convolutional Instance-Aware Semantic Segmentation
- Blog: TRFH: towards real-time face detection and head pose estimation
- Blog: Seamless Scene Segmentation
- Blog: LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception
History & citation
Current · Permanent link
- This direction split from Shared Backbones for Efficient Multi-Task Visual Perception (76% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_shared_backbone_multi_task_learning_10118115,
title = {shared-backbone multi-task learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/shared-backbone-multi-task-learning/rdr_10118115ffc14fdb9fba110fddc01b84},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_shared_backbone_multi_task_learning_10118115_v1,
title = {shared-backbone multi-task learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/shared-backbone-multi-task-learning/rdr_10118115ffc14fdb9fba110fddc01b84/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}