Can I read More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation on EtoBox?

More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation by Catalano, Nico; Maranelli, Alessandro; Chiatti, Agnese; Matteucci, Matteo is a scholarly article available to read on EtoBox.

What is More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation about?

Semantic segmentation is a key prerequisite to robust image understanding for applications in \acrlong{ai} and Robotics. \acrlong{fss}, in particular, concerns the extension and optimization of traditional segmentation methods in challenging conditions where limited training examples are available. A predominant approach in \acrlong{fss} is to rely on a single backbone for visual feature extraction. Choosing which backbone to leverage is a deciding factor contributing to the overall performance. In this work, we interrogate on whether fusing features from different backbones can improve the ability of \acrlong{fss} models to capture richer visual features. To tackle this question, we propose and compare two ensembling techniques-Independent Voting and Feature Fusion. Among the available \acrlong{fss} methods, we implement the proposed ensembling techniques on PANet. The module dedicated to predicting segmentation masks from the backbone embeddings in PANet avoids trainable parameters, creating a controlled `in vitro' setting for isolating the impact of different ensembling strategies. Leveraging the complementary strengths of different backbones, our approach outperforms the origin

Author

Catalano, Nico; Maranelli, Alessandro; Chiatti, Agnese; Matteucci, Matteo

Published

2024

Language

EN