A Creative Weak Supervised Semantic Segmentation for Remote Sensing Images

In weakly supervised semantic segmentation (WSSS) tasks on remote sensing images, it is a common practice to train a classification network from scratch using a large batch of images with a limited number of classes. Subsequently, class activation maps are extracted from the model based on predefined class indices, and these maps are then optimized to obtain pseudolabels. To make this strategy effective when introducing a new class, a substantial amount of data needs to be provided to the model. In this article, we present an innovative framework, RS-TextWS-Seg, designed to efficiently generate high-quality segmentation results for a wide range of remote sensing objects using concise descriptions. Our proposed framework comprises three sequential stages: initially, we undertake parameter fine-tuning of the contrastive language-image pretraining (CLIP) model to swiftly strengthen its capacity for zero-shot detection of a limited number of remote sensing features. Subsequently, we introduce a text-driven background suppression mechanism aimed at deriving class activation maps from the refined CLIP model based on textual cues, while concurrently mitigating background noises. Finally, we use the segment anything model (SAM) to refine the edges of the extracted class activation map. We widely researched the leading-edge methodologies in WSSS and conducted a range of comparative experiments and ablation studies to prove the efficacy of our proposed framework. The research findings underscore that RS-TextWS-Seg outperforms other state-of-the-art methods on renowned datasets such as DLRSD and Potsdam, as well as on bespoke datasets specifically curated for overground petroleum pipelines and oil well fields.