MSI: Maximize Support-Set Information for Few-Shot Segmentation
This work addresses a specific bottleneck in few-shot segmentation for computer vision applications, offering incremental improvements over existing methods.
The paper tackles the problem of few-shot segmentation by addressing an information bottleneck caused by removing background features with support masks, particularly for small targets and inaccurate boundaries. The proposed MSI method improves performance by visible margins and faster convergence across multiple benchmarks.
FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method(MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence. Our code and trained models are available at: https://github.com/moonsh/MSI-Maximize-Support-Set-Information