mlsanityData to 14 Oct 2026

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

arXiv 1612.07695 ↗First posted 22 Dec 2016cs.CV cs.ROcited by 90

Not on the map. Why?

Abstract (arXiv)

While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset, outperforming the state-of-the-art in the road segmentation task. Our approach is also very efficient, taking less than 100 ms to perform all tasks.

Key facts. Cited by 90 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 20; 2023: 23; 2024: 16; 2025: 9; 2026: 3.

90 papers.

Sort:

By area:

  1. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 166
  2. 2021YOLOP: You Only Look Once for Panoptic Driving Perceptioncited by 82
  3. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  4. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  5. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 57
  6. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  7. 2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
  8. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  9. 2022HybridNets: End-to-End Perception Networkcited by 30
  10. 2022Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Drivingcited by 30
  11. 2023Semantic Image Segmentation: Two Decades of Researchcited by 27
  12. 2024EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentationcited by 27
38 more
  1. 2022Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsingcited by 26
  2. 2022YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perceptioncited by 26
  3. 2021Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithmscited by 23
  4. 2024Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectivescited by 23
  5. 2021Deep Multi-Task Learning for Joint Localization, Perception, and Predictioncited by 22
  6. 2021MonoGRNet: A General Framework for Monocular 3D Object Detectioncited by 20
  7. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  8. 2021A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understandingcited by 17
  9. 2022Fast Road Segmentation via Uncertainty-aware Symmetric Networkcited by 17
  10. 2023You Only Look at Once for Real-time and Generic Multi-Taskcited by 14
  11. 2023TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Carscited by 13
  12. 2024SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Imagescited by 13
  13. 2025MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perceptioncited by 10
  14. 2022LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Networkcited by 8
  15. 2023Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Drivingcited by 8
  16. 2023Contrastive Multi-Task Dense Predictioncited by 8
  17. 2021IPatch: A Remote Adversarial Patchcited by 7
  18. 2022Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approachcited by 7
  19. 2023Efficient Controllable Multi-Task Architecturescited by 7
  20. 2021Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Imagescited by 6
  21. 2022Multi-Task Learning for Visual Scene Understandingcited by 6
  22. 2023Multi-Modal Multi-Task (3MT) Road Segmentationcited by 6
  23. 2024DualAD: Dual-Layer Planning for Reasoning in Autonomous Drivingcited by 6
  24. 2024Multitask Learning in Minimally Invasive Surgical Vision: A Reviewcited by 5
  25. 2024TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Drivingcited by 5
  26. 2024RepVF: A Unified Vector Fields Representation for Multi-task 3D Perceptioncited by 5
  27. 2025Temporal Action Detection Model Compression by Progressive Block Dropcited by 5
  28. 2025SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion Modelscited by 5
  29. 2021Instance-Level Task Parameters: A Robust Multi-task Weighting Frameworkcited by 4
  30. 2021Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillationcited by 4
  31. 2022Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoringcited by 4
  32. 2022Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformerscited by 4
  33. 2022Monocular BEV Perception of Road Scenes via Front-to-Top View Projectioncited by 4
  34. 2022Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Frameworkcited by 4
  35. 2024Exploiting Low-level Representations for Ultra-Fast Road Segmentationcited by 4
  36. 2024Hybridnet for depth estimation and semantic segmentationcited by 4
  37. 2024MMCert: Provable Defense against Adversarial Attacks to Multi-modal Modelscited by 4
  38. 2024Panoptic Perception for Autonomous Driving: A Surveycited by 4

50 most cited of 90 All 90 (JSON)