mlsanityData to 13 Oct 2026

Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning

arXiv 2605.17624 ↗First posted 17 May 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on partially labeled datasets with differently structured output tasks. Specifically, we use the popular FixMatch method for invariant semi-supervised learning and its equivariant extension Dense FixMatch. We evaluate their performance on the Cityscapes and BDD100K datasets in the context of the prevalent object detection and semantic segmentation tasks in computer vision. We consider varying sizes of the subsets annotated for each task and different overlaps among them. Our results for both invariant and equivariant semi-supervised learning outperform supervised baselines in most situations, with the most significant improvements observed when fewer labeled samples are available for a task and generally better results for the latter approach. Our study suggests that invariant/equivariant learning is a promising general direction for multi-task learning from limited labeled data.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 45 of its 54 references that are in the map. First posted on arXiv 17 May 2026.

Builds on

45 of 54 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,730
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,435
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,216
  7. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,266
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,082
  9. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  10. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,362
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,306
  12. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,284
33 more
  1. 2016Group Equivariant Convolutional Networkscited by 1,157
  2. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,058
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,055
  4. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 919
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  6. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 509
  7. 2020Rethinking Pre-training and Self-trainingcited by 352
  8. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  9. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  10. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  11. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  12. 2021A Survey on Deep Semi-supervised Learningcited by 250
  13. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 232
  14. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  15. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  16. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  17. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  18. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  19. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  20. 2020Robust Learning Through Cross-Task Consistencycited by 105
  21. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  22. 2018Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotationscited by 51
  23. 2020Knowledge Distillation for Multi-task Learningcited by 51
  24. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  25. 2021Learning Multiple Dense Prediction Tasks from Partially Annotated Datacited by 42
  26. 2016Integrated perception with recurrent multi-task neural networkscited by 24
  27. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
  28. 2018Disjoint Multi-task Learning between Heterogeneous Human-centric Taskscited by 16
  29. 2020Partly Supervised Multitask Learningcited by 11
  30. 2018Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learningcited by 7
  31. 2019Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Povertycited by 4
  32. 2022Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction taskscited by 4
  33. 2022An analysis of over-sampling labeled data in semi-supervised learning with FixMatchcited by 2

Built on by

Not cited yet.