S4: Self-Supervised Sensing Across the Spectrum
원문 초록
Satellite image time series (SITS) segmentation is crucial for many applications like environmental monitoring, land cover mapping and agricultural crop type classification. However, training models for SITS segmentation remains a challenging task due to the lack of abundant training data, which requires fine grained annotation. We propose S4 a new self-supervised pre-training approach that significantly reduces the requirement for labeled training data by utilizing two new insights: (a) Satellites capture images in different parts of the spectrum such as radio frequencies, and visible frequencies. (b) Satellite imagery is geo-registered allowing for fine-grained spatial alignment. We use these insights to formulate pre-training tasks in S4. We also curate m2s2-SITS, a large-scale dataset of unlabeled, spatially-aligned, multi-modal and geographic specific SITS that serves as representative pre-training data for S4. Finally, we evaluate S4 on multiple SITS segmentation datasets and demonstrate its efficacy against competing baselines while using limited labeled data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ClaSP - Time Series Segmentation
A Better Alternative to Piecewise Linear Time Series Segmentation
ECGGuard: Deep Watermarking of Electrocardiogram Signals With Error-Correcting Codes
PulseGuard: rPPG-Derived Temporal Signals as a Forensic Modality for Talking-Face Deepfake Detection
인공 신경망에서 표현 학습을 통한 창발적 일반화
Emergent Generalization by Representation Learning in Artificial Neural Networks
HARN: 이벤트 기반 다중 시간대 예측을 위한 계층적 연상 공명 네트워크
HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting
토론
이 논문과 연결된 포럼 글이 아직 없습니다.