mlsanityData to 14 Oct 2026

Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the CTAO first Large Sized Telescope

arXiv 2608.09630 ↗First posted 10 Aug 2026astro-ph.IM cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation is a widespread set of methods that leverages the knowledge of a labeled source domain to train a model to perform well on a related unlabeled target domain. They generally introduce an auxiliary adaptation-related task that can be integrated into the multitask paradigm, which aims to merge multiple single-task models into a unified architecture. In this paper, we propose to associate domain adaptation and multitask balancing in the realistic context of an extreme class imbalance. Therefore, we propose a combined framework to cover and validate these approaches, and evaluate its performance in the physics-based context of the Cherenkov Telescope Array Observatory (CTAO). Along with a comparative study of some relevant adaptation techniques, we highlight the impact of extreme label shift and extend the investigations on importance weighting to rectify it. The complete code and results are published and available as open-source resources on Zenodo.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 58 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

29 of 58 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  7. 2017Improved Training of Wasserstein GANscited by 2,235
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  9. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  10. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  11. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  12. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
17 more
  1. 2017A Survey on Multi-Task Learningcited by 840
  2. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  3. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  4. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  5. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  6. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  7. 2016Coupled Generative Adversarial Networkscited by 216
  8. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 214
  9. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  10. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  11. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 101
  12. 2020A Review of Single-Source Deep Unsupervised Visual Domain Adaptationcited by 96
  13. 2017Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagerycited by 56
  14. 2023Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learningcited by 51
  15. 2021Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iteratecited by 43
  16. 2018Unsupervised Domain Adaptation: A Multi-task Learning-based Methodcited by 2
  17. 2021First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learningcited by 2

Built on by

Not cited yet.