Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation

TL;DR

This paper introduces UDUN, a novel network architecture for high-accuracy dichotomous image segmentation that effectively combines trunk and structure features for improved precision and real-time performance.

Contribution

The paper proposes a unified network with a dual-input backbone, a divide-and-conquer module, and a trunk-structure aggregation module to enhance segmentation accuracy by effectively decoupling and integrating features.

Findings

Achieves 0.772 weighted F-measure on DIS-TE dataset.

Operates at 65.3 fps with ResNet-18 backbone.

Outperforms state-of-the-art methods across six evaluation metrics.

Abstract

High-accuracy Dichotomous Image Segmentation (DIS) aims to pinpoint category-agnostic foreground objects from natural scenes. The main challenge for DIS involves identifying the highly accurate dominant area while rendering detailed object structure. However, directly using a general encoder-decoder architecture may result in an oversupply of high-level features and neglect the shallow spatial information necessary for partitioning meticulous structures. To fill this gap, we introduce a novel Unite-Divide-Unite Network (UDUN} that restructures and bipartitely arranges complementary features to simultaneously boost the effectiveness of trunk and structure identification. The proposed UDUN proceeds from several strengths. First, a dual-size input feeds into the shared backbone to produce more holistic and detailed features while keeping the model lightweight. Second, a simple Divide-and-Conquer Module (DCM) is proposed to decouple multiscale low- and high-level features into our structure decoder and trunk decoder to obtain structure and trunk information respectively. Moreover, we design a Trunk-Structure Aggregation module (TSA) in our union decoder that performs cascade integration for uniform high-accuracy segmentation. As a result, UDUN performs favorably against state-of-the-art competitors in all six evaluation metrics on overall DIS-TE, i.e., achieving 0.772 weighted F-measure and 977 HCE. Using 1024*1024 input, our model enables real-time inference at 65.3 fps with ResNet-18.