Unsupervised Change Detection in Remote Sensing Images Using CNN Based Transfer Learning

Paul, Josephina; Shankar, B. Uma; Bhattacharyya, Balaram; Datta, Alak Kumar

doi:10.1007/978-3-030-81462-5_42

Cited by 5 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a similar manner, Siamese-style contrastive learning for change detection combines image and domain knowledge contrastive losses during training and uses self-knowledge distillation from the teacher network during inference to enhance change detection accuracy [58]. Other noteworthy studies in the domain of EO imagery-based landcover change detection using self-supervised and unsupervised learning include using Siamese networks with local and global contrastive losses [59], introducing task-specific Siamese-style contrastive learning with hard sampling and smoothing [60], and extracting features from pre-trained CNNs to generate change maps via clustering [61].…”

Section: B Deep Learning For Eo-based Change Detectionmentioning

confidence: 99%

Forest Disturbance Detection via Self-Supervised and Transfer Learning With Sentinel-1&2 Images

Kuzu,

Antropov,

Molinier

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this study, we examine the potential of leveraging self-supervised learning (SSL) and transfer learning methodologies for forest disturbance mapping using Earth Observation (EO) data. Our focus is on natural disturbances caused by windthrow and snowload damages. Particularly, we investigate the potential of knowledge distillation-based contrastive learning approaches to obtain comprehensive representations of forest structure changes using Copernicus Sentinel-1 and Sentinel-2 satellite imagery. Leveraging pre-trained backbone models from knowledge distillation, we employ transfer learning based on Deep Change Vector Analysis (DCVA) to delineate forest changes. We demonstrate developed approaches on two use-cases, namely mapping windthown forest using bi-temporal Sentinel-1 and Sentinel-2 images, and mapping forest areas damaged by excessive snowload using bi-temporal Sentinel-1 images. Developed self-supervised models were compared in a benchmarking exercise. The best results were provided by pixel-level contrastive learning for Sentinel-1 based snowload damage mapping with an overall accuracy of 84% and F1 score of 0.567, and for Sentinel-2 based forest windthrow mapping with an overall accuracy of 76.5% and F1 score of 0.692. We expect that developed methodologies can be useful for mapping also other types of forest disturbances using Copernicus Sentinel images or similar EO data. Our findings underscore the potential of SSL and transfer learning for enhancing forest disturbance detection using EO.

show abstract