Weakly Supervised Salient Object Detection Using Image Labels

TL;DR

This paper introduces a weakly supervised method for salient object detection that combines classification-based activation maps with unsupervised saliency maps, iteratively refining labels to achieve high accuracy without extensive pixel-level annotations.

Contribution

It proposes a novel iterative training algorithm using a graphical model and fully convolutional networks to improve saliency detection with noisy, weak labels derived from image-level supervision.

Findings

Outperforms all state-of-the-art unsupervised methods.

Achieves comparable results to strongly-supervised methods on benchmarks.

Effectively reduces labeling ambiguity through iterative refinement.

Abstract

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure. In this paper, we note that superior salient object detection can be obtained by iteratively mining and correcting the labeling ambiguity on saliency maps from traditional unsupervised methods. We propose to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develop a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations. Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating. The graphical model corrects the internal labeling ambiguity through spatial consistency and structure preserving while the fully convolutional network helps to correct the cross-image semantic ambiguity and simultaneously update the coarse activation map for next iteration. Experimental results demonstrate that our proposed method greatly outperforms all state-of-the-art unsupervised saliency detection methods and can be comparable to the current best strongly-supervised methods training with thousands of pixel-level saliency map annotations on all public benchmarks.