mlsanityData to 14 Oct 2026

Context-self contrastive pretraining for crop type semantic segmentation

arXiv 2104.04310 ↗First posted 9 Apr 2021cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a fully supervised pre-training scheme based on contrastive learning particularly tailored to dense classification tasks. The proposed Context-Self Contrastive Loss (CSCL) learns an embedding space that makes semantic boundaries pop-up by use of a similarity metric between every location in a training sample and its local context. For crop type semantic segmentation from Satellite Image Time Series (SITS) we find performance at parcel boundaries to be a critical bottleneck and explain how CSCL tackles the underlying cause of that problem, improving the state-of-the-art performance in this task. Additionally, using images from the Sentinel-2 (S2) satellite missions we compile the largest, to our knowledge, SITS dataset densely annotated by crop type and parcel identities, which we make publicly available together with the data generation pipeline. Using that data we find CSCL, even with minimal pre-training, to improve all respective baselines and present a process for semantic segmentation at super-resolution for obtaining crop classes at a more granular level. The code and instructions to download the data can be found in https://github.com/michaeltrs/DeepSatModels.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 42 of its 73 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

42 of 73 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  11. 2020Supervised Contrastive Learningcited by 2,829
  12. 2017Non-local Neural Networkscited by 2,293
30 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  2. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  4. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  5. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  6. 2018Self-Attention with Relative Position Representationscited by 1,120
  7. 2020Contrastive Learning with Hard Negative Samplescited by 628
  8. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  9. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  10. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  11. 2019PointRend: Image Segmentation as Renderingcited by 440
  12. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  13. 2019Attention Augmented Convolutional Networkscited by 363
  14. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 328
  15. 2020A Metric Learning Reality Checkcited by 321
  16. 2016Lip Reading Sentences in the Wildcited by 228
  17. 2018Deep learning in agriculture: A surveycited by 160
  18. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  19. 2014Material Recognition in the Wild with the Materials in Context Databasecited by 79
  20. 2018Temporal Convolutional Neural Network for the Classification of Satellite Image Time Seriescited by 76
  21. 2019Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attentioncited by 71
  22. 2018Multi-Temporal Land Cover Classification with Sequential Recurrent Encoderscited by 61
  23. 2019BreizhCrops: A Time Series Dataset for Crop Type Mappingcited by 34
  24. 2016Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networkscited by 25
  25. 2015Fully Connected Deep Structured Networkscited by 24
  26. 2017Land Cover Classification via Multi-temporal Spatial Data by Recurrent Neural Networkscited by 19
  27. 2019Time-Space tradeoff in deep learning models for crop classification on satellite multi-spectral image time seriescited by 18
  28. 2018Semi-Supervised Learning via Compact Latent Space Clusteringcited by 15
  29. 2018DuPLO: A DUal view Point deep Learning architecture for time series classificatiOncited by 14
  30. 2019Distance transform regression for spatially-aware deep semantic segmentationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 6; 2025: 0; 2026: 1.

11 papers.

  1. 2023ViTs for SITS: Vision Transformers for Satellite Image Time Seriescited by 56
  2. 2024Deep Learning for Satellite Image Time Series Analysis: A Reviewcited by 13
  3. 2022Semi-Supervised Semantic Segmentation with Cross Teacher Trainingcited by 11
  4. 2022Embedding Earth: Self-supervised contrastive pre-training for dense land cover classificationcited by 6
  5. 2024Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentationcited by 4
  6. 2021DeepSatData: Building large scale datasets of satellite images for training machine learning modelscited by 2
  7. 2024Detecting Looted Archaeological Sites from Satellite Image Time Seriescited by 2
  8. 2024VistaFormer: Scalable Vision Transformers for Satellite Image Time Series Segmentationcited by 1
  9. 2024Low-Resource Crop Classification from Multi-Spectral Time Series Using Lossless Compressorscited by 0
  10. 2024Semantic-Aware Representation of Multi-Modal Data for Data Ingress: A Literature Reviewcited by 0
  11. 2026TEA: Temporal Adaptive Satellite Image Semantic Segmentationcited by 0