Image change detection with only a few samples
This addresses the challenge of few annotations for image change detection, offering a solution for scenarios with limited data, though it is incremental as it builds on existing methods.
The paper tackles the problem of poor generalization in image change detection due to limited annotated datasets by proposing synthetic data generation using simple image processing methods and an early fusion network, achieving higher generalization ability than models trained on insufficient real-world data across six test sets.
This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image change detection task is the lack of large annotated datasets covering a wide variety of scenes. Change detection models trained on insufficient datasets have shown poor generalization capability. To address the poor generalization issue, we propose using simple image processing methods for generating synthetic but informative datasets, and design an early fusion network based on object detection which could outperform the siamese neural network. Our key insight is that the synthetic data enables the trained model to have good generalization ability for various scenarios. We compare the model trained on the synthetic data with that on the real-world data captured from a challenging dataset, CDNet, using six different test sets. The results demonstrate that the synthetic data is informative enough to achieve higher generalization ability than the insufficient real-world data. Besides, the experiment shows that utilizing a few (often tens of) samples to fine-tune the model trained on the synthetic data will achieve excellent results.