Selectivity or Invariance: Boundary-aware Salient Object Detection

TL;DR

This paper introduces a boundary-aware network with successive dilation for salient object detection, balancing feature selectivity at boundaries and invariance at interiors to improve detection accuracy.

Contribution

It proposes a novel network architecture with boundary localization, interior perception, and transition compensation streams, along with a successive dilation module, to address the selectivity-invariance dilemma in SOD.

Findings

Outperforms 16 state-of-the-art methods on six datasets.

Enhances boundary localization accuracy.

Improves interior feature invariance.

Abstract

Typically, a salient object detection (SOD) model faces opposite requirements in processing object interiors and boundaries. The features of interiors should be invariant to strong appearance change so as to pop-out the salient object as a whole, while the features of boundaries should be selective to slight appearance change to distinguish salient objects and background. To address this selectivity-invariance dilemma, we propose a novel boundary-aware network with successive dilation for image-based SOD. In this network, the feature selectivity at boundaries is enhanced by incorporating a boundary localization stream, while the feature invariance at interiors is guaranteed with a complex interior perception stream. Moreover, a transition compensation stream is adopted to amend the probable failures in transitional regions between interiors and boundaries. In particular, an integrated successive dilation module is proposed to enhance the feature invariance at interiors and transitional regions. Extensive experiments on six datasets show that the proposed approach outperforms 16 state-of-the-art methods.