mlsanityData to 14 Oct 2026

Tampered VAE for Improved Satellite Image Time Series Classification

arXiv 2203.16149 ↗First posted 30 Mar 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The unprecedented availability of spatial and temporal high-resolution satellite image time series (SITS) for crop type mapping is believed to necessitate deep learning architectures to accommodate challenges arising from both dimensions. Recent state-of-the-art deep learning models have shown promising results by stacking spatial and temporal encoders. However, we present a Pyramid Time-Series Transformer (PTST) that operates solely on the temporal dimension, i.e., neglecting the spatial dimension, can produce superior results with a drastic reduction in GPU memory consumption and easy extensibility. Furthermore, we augment it to perform semi-supervised learning by proposing a classification-friendly VAE framework that introduces clustering mechanisms into latent space and can promote linear separability therein. Consequently, a few principal axes of the latent space can explain the majority of variance in raw data. Meanwhile, the VAE framework with proposed tweaks can maintain competitive classification performance as its purely discriminative counterpart when only 40% of labelled data is used. We hope the proposed framework can serve as a baseline for crop classification with SITS for its modularity and simplicity.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

34 of 46 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2013Auto-Encoding Variational Bayescited by 4,053
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  9. 2016Density estimation using Real NVPcited by 2,042
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  12. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
22 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  2. 2019An Introduction to Variational Autoencoderscited by 1,000
  3. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  4. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  5. 2015Generating Sentences from a Continuous Spacecited by 612
  6. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  7. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  8. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 387
  9. 2017VAE with a VampPriorcited by 248
  10. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  11. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  12. 2016Variational Lossy Autoencodercited by 176
  13. 2019Transformers without Tears: Improving the Normalization of Self-Attentioncited by 153
  14. 2014A* Samplingcited by 151
  15. 2018The Best of Both Worlds: Combining Recent Advances in Neural Machine Translationcited by 102
  16. 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
  17. 2018Temporal Convolutional Neural Network for the Classification of Satellite Image Time Seriescited by 76
  18. 2019Self-attention for raw optical Satellite Time Series Classificationcited by 75
  19. 2019Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attentioncited by 71
  20. 2018Multi-Temporal Land Cover Classification with Sequential Recurrent Encoderscited by 61
  21. 2020Lightweight Temporal Self-Attention for Classifying Satellite Image Time Seriescited by 55
  22. 2018Variational Semi-supervised Aspect-term Sentiment Analysis via Transformercited by 7

Built on by

Not cited yet.