SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond

TL;DR

This paper introduces a new benchmark dataset and a deep learning model called SRN for detecting object reflection symmetry in complex, real-world images, advancing symmetry detection in unconstrained environments.

Contribution

The paper presents a novel benchmark dataset, Sym-PASCAL, and proposes the side-output residual network (SRN), a new deep learning architecture that improves symmetry detection accuracy in challenging scenarios.

Findings

SRN achieves state-of-the-art performance on Sym-PASCAL.

The benchmark captures complex real-world symmetry detection challenges.

Multi-task SRN effectively performs symmetry and edge detection.

Abstract

In this paper, we establish a baseline for object reflection symmetry detection in complex backgrounds by presenting a new benchmark and an end-to-end deep learning approach, opening up a promising direction for symmetry detection in the wild. The new benchmark, Sym-PASCAL, spans challenges including object diversity, multi-objects, part-invisibility, and various complex backgrounds that are far beyond those in existing datasets. The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the object ground-truth symmetry and the side-outputs of multiple stages. By cascading RUs in a deep-to-shallow manner, SRN exploits the 'flow' of errors among multiple stages to address the challenges of fitting complex output with limited convolutional layers, suppressing the complex backgrounds, and effectively matching object symmetry at different scales. SRN is further upgraded to a multi-task side-output residual network (MT-SRN) for joint symmetry and edge detection, demonstrating its generality to image-to-mask learning tasks. Experimental results validate both the challenging aspects of Sym-PASCAL benchmark related to real-world images and the state-of-the-art performance of the proposed SRN approach.