Few-Shot Segmentation (FSS) is challenging for limited support images and large intra-class appearance discrepancies. Most existing approaches focus on extracting high-level representations of the same layers for support-query correlations, neglecting the shift issue between different layers and scales, due to the huge difference between support and query samples. In this paper, we propose a Multi-Content Interaction Network (MCINet) to remedy this issue by fully exploiting and interacting with the multi-scale contextual information contained in the support-query pairs to supplement the same-layer correlations. Specifically, MCINet improves FSS from the perspectives of boosting the query representations by incorporating the low-level structural information from another query branch into the high-level semantic features, enhancing the support-query correlations by exploiting both the same-layer and adjacent-layer features, and refining the predicted results by a multi-scale mask prediction strategy, with which the different scale contents have bidirectionally interacted. Experiments on two benchmarks demonstrate that our approach reaches SOTA performances and outperforms the best competitors with many desirable advantages, especially on the challenging COCO dataset.

翻译：少样本分割（FSS）面临支撑图像有限及类内表观差异大的挑战。现有方法大多关注提取同层高级表示进行支撑-查询相关性计算，忽略了支撑样本与查询样本间巨大差异导致的跨层与跨尺度迁移问题。本文提出多内容交互网络（MCINet），通过充分挖掘和交互支撑-查询对中包含的多尺度上下文信息来补充同层相关性。具体而言，MCINet从三个维度提升FSS性能：将另一查询分支的低层结构信息融入高层语义特征以增强查询表示；同时利用同层与邻层特征强化支撑-查询相关性；通过多尺度掩码预测策略实现不同尺度内容的双向交互，优化预测结果。在两个基准数据集上的实验表明，本方法取得了最先进性能，并在多个优势指标上超越最佳对比方法，尤其在具有挑战性的COCO数据集上表现突出。