A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels

TL;DR

This paper introduces a weakly-supervised learning framework for salient object detection that leverages hybrid labels, combining coarse and real labels, and employs a dual-network training strategy with label refinement to achieve competitive results.

Contribution

The paper proposes a novel weakly-supervised SOD framework using hybrid labels and a dual-network approach with specialized training strategies for improved label refinement and detection accuracy.

Findings

Achieves competitive performance on five SOD benchmarks.

Effectively handles label noise and imbalance with new training strategies.

Demonstrates the feasibility of weakly-supervised SOD with hybrid labels.

Abstract

Fully-supervised salient object detection (SOD) methods have made great progress, but such methods often rely on a large number of pixel-level annotations, which are time-consuming and labour-intensive. In this paper, we focus on a new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels. To address the issues of label noise and quantity imbalance in this task, we design a new pipeline framework with three sophisticated training strategies. In terms of model framework, we decouple the task into label refinement sub-task and salient object detection sub-task, which cooperate with each other and train alternately. Specifically, the R-Net is designed as a two-stream encoder-decoder model equipped with Blender with Guidance and Aggregation Mechanisms (BGA), aiming to rectify the coarse labels for more reliable pseudo-labels, while the S-Net is a replaceable SOD network supervised by the pseudo labels generated by the current R-Net. Note that, we only need to use the trained S-Net for testing. Moreover, in order to guarantee the effectiveness and efficiency of network training, we design three training strategies, including alternate iteration mechanism, group-wise incremental mechanism, and credibility verification mechanism. Experiments on five SOD benchmarks show that our method achieves competitive performance against weakly-supervised/unsupervised methods both qualitatively and quantitatively.