SITSMamba for Crop Classification based on Satellite Image Time Series
Xiaolei Qin, Xin Su, Liangpei Zhang

TL;DR
This paper introduces SITSMamba, a novel deep learning model combining CNN and Mamba architectures for crop classification from satellite image time series, leveraging dual-task learning and positional weighting to improve temporal feature extraction.
Contribution
It proposes a new SITSMamba model integrating CNN and Mamba for enhanced temporal representation in SITS crop classification, with a dual-branch decoder and positional weighting.
Findings
Improved crop classification accuracy over existing methods.
Effective exploitation of temporal information through dual-branch decoding.
Enhanced learning of latent temporal features with positional weighting.
Abstract
Satellite image time series (SITS) data provides continuous observations over time, allowing for the tracking of vegetation changes and growth patterns throughout the seasons and years. Numerous deep learning (DL) approaches using SITS for crop classification have emerged recently, with the latest approaches adopting Transformer for SITS classification. However, the quadratic complexity of self-attention in Transformer poses challenges for classifying long time series. While the cutting-edge Mamba architecture has demonstrated strength in various domains, including remote sensing image interpretation, its capacity to learn temporal representations in SITS data remains unexplored. Moreover, the existing SITS classification methods often depend solely on crop labels as supervision signals, which fails to fully exploit the temporal information. In this paper, we proposed a Satellite Image…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRemote Sensing and Land Use · Advanced Computational Techniques and Applications · Food Supply Chain Traceability
MethodsAttention Is All You Need · Byte Pair Encoding · Absolute Position Encodings · Softmax · Mamba: Linear-Time Sequence Modeling with Selective State Spaces · Label Smoothing · Layer Normalization · Dropout · Position-Wise Feed-Forward Layer · Residual Connection
