mlsanityData to 7 Oct 2026

Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification

arXiv 2204.03144 ↗First posted 7 Apr 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

A pretrain-finetune strategy is widely used to reduce the overfitting that can occur when data is insufficient for CNN training. First few layers of a CNN pretrained on a large-scale RGB dataset are capable of acquiring general image characteristics which are remarkably effective in tasks targeted for different RGB datasets. However, when it comes down to hyperspectral domain where each domain has its unique spectral properties, the pretrain-finetune strategy no longer can be deployed in a conventional way while presenting three major issues: 1) inconsistent spectral characteristics among the domains (e.g., frequency range), 2) inconsistent number of data channels among the domains, and 3) absence of large-scale hyperspectral dataset. We seek to train a universal cross-domain model which can later be deployed for various spectral domains. To achieve, we physically furnish multiple inlets to the model while having a universal portion which is designed to handle the inconsistent spectral characteristics among different domains. Note that only the universal portion is used in the finetune process. This approach naturally enables the learning of our model on multiple domains simultaneously which acts as an effective workaround for the issue of the absence of large-scale dataset. We have carried out a study to extensively compare models that were trained using cross-domain approach with ones trained from scratch. Our approach was found to be superior both in accuracy and in training efficiency. In addition, we have verified that our approach effectively reduces the overfitting issue, enabling us to deepen the model up to 13 layers (from 9) without compromising the accuracy.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 32 of its 73 references that are in the map. First posted on arXiv 7 Apr 2022.

Builds on

32 of 73 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  12. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
20 more
  1. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  2. 2018Rethinking ImageNet Pre-trainingcited by 376
  3. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  4. 2019HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classificationcited by 91
  5. 2016Going Deeper with Contextual CNN for Hyperspectral Image Classificationcited by 58
  6. 2018Three dimensional Deep Learning approach for remote sensing image classificationcited by 50
  7. 2017Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Networkcited by 16
  8. 2020Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learningcited by 16
  9. 2019Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classificationcited by 15
  10. 2018HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Imagecited by 14
  11. 2017ME R-CNN: Multi-Expert R-CNN for Object Detectioncited by 13
  12. 2016Weakly Supervised Localization using Deep Feature Mapscited by 7
  13. 2018Cross-domain CNN for Hyperspectral Image Classificationcited by 5
  14. 2019Is Pretraining Necessary for Hyperspectral Image Classification?cited by 4
  15. 2018Generating Hard Examples for Pixel-wise Classificationcited by 3
  16. 2017IOD-CNN: Integrating Object Detection Networks for Event Recognitioncited by 2
  17. 2018A CNN-based Spatial Feature Fusion Algorithm for Hyperspectral Imagery Classificationcited by 2
  18. 2018DOD-CNN: Doubly-injecting Object Information for Event Recognitioncited by 2
  19. 2019S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognitioncited by 2
  20. 2016Fast Object Localization Using a CNN Feature Map Based Multi-Scale Searchcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 4.

5 papers.

  1. 2025SPECIAL: Zero-shot Hyperspectral Image Classification With CLIPcited by 4
  2. 2023Hyperspectral Benchmark: Bridging the Gap between HSI Applications through Comprehensive Dataset and Pretrainingcited by 3
  3. 2025FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classificationcited by 0
  4. 2025Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integrationcited by 0
  5. 2025Agreement Disagreement Guided Knowledge Transfer for Cross-Scene Hyperspectral Imagingcited by 0