mlsanityData to 7 Oct 2026

Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data

arXiv 2311.04040 ↗First posted 7 Nov 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Multi-task partially annotated data where each data point is annotated for only a single task are potentially helpful for data scarcity if a network can leverage the inter-task relationship. In this paper, we study the joint learning of object detection and semantic segmentation, the two most popular vision problems, from multi-task data with partial annotations. Extensive experiments are performed to evaluate each task performance and explore their complementarity when a multi-task network cannot optimize both tasks simultaneously. We propose employing knowledge distillation to leverage joint-task optimization. The experimental results show favorable results for multi-task learning and knowledge distillation over single-task learning and even full supervision scenario. All code and data splits are available at https://github.com/lhoangan/multas

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 7 Nov 2023.

Builds on

29 of 35 references.

References · 29

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017Mask R-CNNcited by 7,259
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  7. 2018Path Aggregation Network for Instance Segmentationcited by 796
  8. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  9. 2019Panoptic Feature Pyramid Networkscited by 644
  10. 2018Born Again Neural Networkscited by 539
  11. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  12. 2020Rethinking Pre-training and Self-trainingcited by 352
17 more
  1. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  2. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  3. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 113
  4. 2020Robust Learning Through Cross-Task Consistencycited by 105
  5. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  6. 2019BAM! Born-Again Multi-Task Networks for Natural Language Understandingcited by 85
  7. 2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75
  8. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  9. 2020Knowledge Distillation for Multi-task Learningcited by 51
  10. 2020Automated Search for Resource-Efficient Branched Multi-Task Networkscited by 51
  11. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  12. 2021Learning Multiple Dense Prediction Tasks from Partially Annotated Datacited by 42
  13. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  14. 2018ScratchDet: Training Single-Shot Object Detectors from Scratchcited by 19
  15. 2020Taskology: Utilizing Task Relations at Scalecited by 19
  16. 2020Partly Supervised Multitask Learningcited by 11
  17. 2023Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasetscited by 1
  2. 2024Box for Mask and Mask for Box: weak losses for multi-task partially supervised learningcited by 0
  3. 2025Enhancing deep learning performance on burned area delineation from SPOT-6/7 imagery for emergency managementcited by 0