mlsanityData to 14 Oct 2026

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

arXiv 2308.15081 ↗First posted 29 Aug 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data, which has broad prospects in various earth vision applications. However, when PU learning meets limited labeled HSI, the unlabeled data may dominate the optimization process, which makes the neural networks overfit the unlabeled data. In this paper, a Taylor variational loss is proposed for HSI PU learning, which reduces the weight of the gradient of the unlabeled data by Taylor series expansion to enable the network to find a balance between overfitting and underfitting. In addition, the self-calibrated optimization strategy is designed to stabilize the training process. Experiments on 7 benchmark datasets (21 tasks in total) validate the effectiveness of the proposed method. Code is at: https://github.com/Hengwei-Zhao96/T-HOneCls.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 19 of its 48 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

19 of 48 references.

References · 19

  1. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  2. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  4. 2017A Closer Look at Memorization in Deep Networkscited by 942
  5. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  6. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  7. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  8. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  9. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 219
  10. 2020Does label smoothing mitigate label noise?cited by 204
  11. 2020A Survey of Label-noise Representation Learning: Past, Present and Futurecited by 122
  12. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
7 more
  1. 2016Mixture Proportion Estimation via Kernel Embedding of Distributionscited by 67
  2. 2022Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspectivecited by 38
  3. 2019Cascaded Recurrent Neural Networks for Hyperspectral Image Classificationcited by 31
  4. 2014PU Learning for Matrix Completioncited by 30
  5. 2020FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classificationcited by 28
  6. 2022Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimizationcited by 8
  7. 2022One-Class Risk Estimation for One-Class Hyperspectral Image Classificationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 2.

8 papers.

  1. 2025HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagerycited by 17
  2. 2024C3DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theoriescited by 1
  3. 2025Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learningcited by 1
  4. 2026AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learningcited by 1
  5. 2025HOpenCls: Training Hyperspectral Image Open-Set Classifiers in Their Living Environmentscited by 0
  6. 2025From Image- to Pixel-level: Label-efficient Hyperspectral Image Reconstructioncited by 0
  7. 2025Needles in the Landscape: Semi-Supervised Pseudolabeling for Archaeological Site Discovery under Label Scarcitycited by 0
  8. 2026Mapping melliferous tree species in Kenya via one-class classification with hyperspectral unsupervised domain adaptationcited by 0