Semantic segmentation involves labeling each pixel in an image with a corresponding class label, enabling detailed scene understanding. In dynamic environments, where conditions change over time, incremental learning techniques are essential for updating segmentation models with newly acquired data. However, incremental segmentation faces the challenge of catastrophic forgetting, where models lose previously learned knowledge when trained on new data distributions. To address this, we propose a recall-based knowledge distillation approach for stable segmentation model training across dynamic environments. Our method combines the strengths of knowledge distillation and recall learning to enhance the model’s ability to recall information from previous data distributions while adapting to new ones. By reintroducing a small portion of the previous dataset during training and applying tailored distillation techniques, our approach mitigates catastrophic forgetting and improves the robustness of these models. Through comprehensive evaluations, we demonstrate the effectiveness of our approach in two scenarios: salt segmentation in seismic datasets and tumor segmentation in MRI datasets. Our method offers a promising solution for addressing the challenges of catastrophic forgetting in incremental semantic segmentation, facilitating the development of more adaptive and reliable computer vision systems in dynamic environments.