Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation

Existing few-shot semantic segmentation methods typically rely on a one-way flow of category information from support to query, ignoring the impact of intra-class diversity. To address this, drawing inspiration from cybernetics, we introduce a Query Feedback Branch (QFB) to propagate query information back to support, generating a query-related support prototype that is more aligned with the query. Subsequently, a Query Amplifier Branch (QAB) is employed to amplify target objects in the query using the acquired support prototype. To further improve the model, we propose a Query Rectification Module (QRM), which utilizes the prediction disparity in the query before and after support activation to identify challenging positive and negative samples from ambiguous regions for query self-rectification. Furthermore, we integrate the QFB, QAB, and QRM into a feedback and rectification layer and incorporate it into an iterative pipeline. This configuration enables the progressive enhancement of bidirectional reciprocative flow of category information between query and support, effectively providing query-adaptive support information and addressing the intra-class diversity problem. Extensive experiments conducted on both PASCAL-5 i and COCO-20 i datasets validate the effectiveness of our approach. The code is available at https://github.com/LIUYUANWEI98/IFRNet . Figure 1. Comparison between existing framework (a)&(b) and our approach (c) for FSS. The red dotted line indicates the information flow of category information. (a) The category information is extracted from support and flows into the query to identify target objects. (b) The category information simultaneously flows from support and query into the intermediate representation. However, in our method (c), the category information circulates bidirectionally between query and support, which could be more compatible with target object in the query.