Few-Shot Semantic Segmentation for Consumer Electronics: An Inter-Class Relation Mining Approach

Huafei Huang, Xu Yuan, Shuo Yu, Wenhong Zhao, Osama Alfarraj, Amr Tolba, Feng Xia

Abstract: Few-shot semantic segmentation (FSS), which can perform segmentation using only a limited number of annotated examples, is a promising technique that has been embedded in many electronic products. Existing approaches usually achieve segmentation for the query image by computing the similarity between the support and query images. However, when segmenting a new query image, the model prediction may be interfered with by distinct classes with similar semantic information, leading to unsatisfactory results. This may greatly weaken the generalization of FSS in real-world scenarios. In response to this challenge, we propose a few-shot semantic segmentation model based on inter-class relation mining named IRMNet. Firstly, we devise a class filter module that accurately selects useful semantic information by mining the class relations between the query and support images. Then, we use a class generation module that applies a diffusion model to generate rough segmentation masks for query images to augment supervision signals. Finally, we conduct extensive experiments on the PASCAL- $5^{i}$ and FSS-1000 datasets. The evaluation results show that IRMNet can achieve superior performance compared to other baselines. The advancement of FSS in this work can contribute to enhancing visual intelligence in real-world consumer electronics.