mlsanityData to 7 Oct 2026

Multi-Task Learning for Robot Perception with Imbalanced Data

arXiv 2602.01899 ↗First posted 2 Feb 2026cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-task problem solving has been shown to improve the accuracy of the individual tasks, which is an important feature for robots, as they have a limited resource. However, when the number of labels for each task is not equal, namely imbalanced data exist, a problem may arise due to insufficient number of samples, and labeling is not very easy for mobile robots in every environment. We propose a method that can learn tasks even in the absence of the ground truth labels for some of the tasks. We also provide a detailed analysis of the proposed method. An interesting finding is related to the interaction of the tasks. We show a methodology to find out which tasks can improve the performance of other tasks. We investigate this by training the teacher network with the task outputs such as depth as inputs. We further provide empirical evidence when trained with a small amount of data. We use semantic segmentation and depth estimation tasks on different datasets, NYUDv2 and Cityscapes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 2 Feb 2026.

Builds on

14 of 24 references.

References · 14

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  3. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  4. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  5. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  6. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  7. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  8. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  9. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  10. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  11. 2020Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systemscited by 34
  12. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
2 more
  1. 2022Trace norm regularization for multi-task learning with scarce datacited by 10
  2. 2023Multi-Modal Multi-Task (3MT) Road Segmentationcited by 6

Built on by

Not cited yet.