In the later training stages, further improvement of the models ability to determine changes relies on how well the change detection (CD) model learns hard cases; however, there are two additional challenges to learning hard case samples: (1) change labels are limited and tend to pointer only to foreground targets, yet hard case samples are prevalent in the background, which leads to optimizing the loss function focusing on the foreground targets and ignoring the background hard cases, which we call imbalance. (2) Complex situations, such as light shadows, target occlusion, and seasonal changes, induce hard case samples, and in the absence of both supervisory and scene information, it is difficult for the model to learn hard case samples directly to accurately obtain the feature representations of the change information, which we call missingness. We propose a Siamese foreground association-driven hard case sample optimization network (HSONet). To deal with this imbalance, we propose an equilibrium optimization loss function to regulate the optimization focus of the foreground and background, determine the hard case samples through the distribution of the loss values, and introduce dynamic weights in the loss term to gradually shift the optimization focus of the loss from the foreground to the background hard cases as the training progresses. To address this missingness, we understand hard case samples with the help of the scene context, propose the scene-foreground association module, use potential remote sensing spatial scene information to model the association between the target of interest in the foreground and the related context to obtain scene embedding, and apply this information to the feature reinforcement of hard cases. Experiments on four public datasets show that HSONet outperforms current state-of-the-art CD methods, particularly in detecting hard case samples.
The existing change detection(CD) methods can be summarized as the visual-first change detection (ViFi-CD) paradigm, which first extracts change features from visual differences and then assigns them specific semantic information. However, CD is essentially dependent on change regions of interest (CRoIs), meaning that the CD results are directly determined by the semantics changes of interest, making its primary image factor semantic of interest rather than visual. The ViFi-CD paradigm can only assign specific semantics of interest to specific change features extracted from visual differences, leading to the inevitable omission of potential CRoIs and the inability to adapt to different CRoI CD tasks. In other words, changes in other CRoIs cannot be detected by the ViFi-CD method without retraining the model or significantly modifying the method. This paper introduces a new CD paradigm, the semantic-first CD (SeFi-CD) paradigm. The core idea of SeFi-CD is to first perceive the dynamic semantics of interest and then visually search for change features related to the semantics. Based on the SeFi-CD paradigm, we designed Anything You Want Change Detection (AUWCD). Experiments on public datasets demonstrate that the AUWCD outperforms the current state-of-the-art CD methods, achieving an average F1 score 5.01\% higher than that of these advanced supervised baselines on the SECOND dataset, with a maximum increase of 13.17\%. The proposed SeFi-CD offers a novel CD perspective and approach.
Remote sensing image semantic segmentation faces substantial challenges in training and transferring models across images with varying resolutions. This issue can be effectively mitigated by continuously learning knowledge derived from new resolutions; however, this learning process is severely plagued by catastrophic forgetting. To address this problem, this paper proposes a novel continual learning framework termed Language-Guided Resolution-Continual Learning (i.e., LaGu-RCL), which alleviates catastrophic forgetting through two complementary strategies. On the one hand, a multi-resolution image augmentation pipeline is introduced to synthesize higher- and lower-resolution variants for each training batch, allowing the model to learn from images of diverse resolutions at every training step. On the other hand, a language-guided learning strategy is proposed to aggregate features of the same resolution while separating those of different resolutions. This ensures that the knowledge acquired from previously learned resolutions is not disrupted by that from unseen resolutions, thereby mitigating catastrophic forgetting. To validate the effectiveness of the proposed approach, we construct MR-ExcavSeg, a multi-resolution dataset covering several counties in Chongqing, and conduct comparative experiments between LaGu-RCL and several state-of-the-art continual learning baselines. Experimental results demonstrate that LaGu-RCL achieves significantly superior segmentation performance and continual learning capability, verifying its advantages.
1 January 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing