# Exploring Self-Attention for Crop-type Classification Explainability

arXiv: https://arxiv.org/abs/2210.13167 · HTML: https://mlsanity.com/paper/2210.13167/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [Self-attention for raw optical Satellite Time Series Classification](https://mlsanity.com/paper/1910.10536/) (2019)
- [Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention](https://mlsanity.com/paper/1911.07757/) (2019)
- [Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series](https://mlsanity.com/paper/2007.00586/) (2020)
- [Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series](https://mlsanity.com/paper/2112.07558/) (2021)
- [Is Sparse Attention more Interpretable?](https://mlsanity.com/paper/2106.01087/) (2021)
- [Interpretable Spatio-temporal Attention for Video Action Recognition](https://mlsanity.com/paper/1810.04511/) (2018)

## Built on by (most cited first, 3 of 3)

- [Adaptive Fusion of Multi-view Remote Sensing data for Optimal Sub-field Crop Yield Prediction](https://mlsanity.com/paper/2401.11844/) (2024)
- [Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correction](https://mlsanity.com/paper/2505.06905/) (2025)
- [Enhanced Infield Agriculture with Interpretable Machine Learning Approaches for Crop Classification](https://mlsanity.com/paper/2408.12426/) (2024)

## Abstract (arXiv)

Transformer models have become a promising approach for crop-type classification. Although their attention weights can be used to understand the relevant time points for crop disambiguation, the validity of these insights depends on how closely the attention weights approximate the actual workings of these black-box models, which is not always clear. In this paper, we introduce a novel explainability framework that systematically evaluates the explanatory power of the attention weights of a standard transformer encoder for crop-type classification. Our results show that attention patterns strongly relate to key dates, which are often associated with critical phenological events for crop-type classification. Further, the sensitivity analysis reveals the limited capability of the attention weights to characterize crop phenology as the identified phenological events depend on the other crops considered during training. This limitation highlights the relevance of future work towards the development of deep learning approaches capable of automatically learning the temporal vegetation dynamics for accurate crop disambiguation