A Causal Debiasing Framework for Unsupervised Salient Object Detection

Unsupervised Salient Object Detection (USOD) is a promising yet challenging task that aims to learn a salient object detection model without any ground-truth labels. Selfsupervised learning based methods have achieved remarkable success recently and have become the dominant approach in USOD. However, we observed that two distribution biases of salient objects limit further performance improvement of the USOD methods, namely, contrast distribution bias and spatial distribution bias. Concretely, contrast distribution bias is essentially a confounder that makes images with similar high-level semantic contrast and/or low-level visual appearance contrast spuriously dependent, thus forming data-rich contrast clusters and leading the training process biased towards the data-rich contrast clusters in the data. Spatial distribution bias means that the position distribution of all salient objects in a dataset is concentrated on the center of the image plane, which could be harmful to off-center objects prediction. This paper proposes a causal based debiasing framework to disentangle the model from the impact of such biases. Specifically, we use causal intervention to perform deconfounded model training to minimize the contrast distribution bias and propose an image-level weighting strategy that softly weights each image’s importance according to the spatial distribution bias map. Extensive experiments on 6 benchmark datasets show that our method significantly outperforms previous unsupervised state-of-the-art methods and even surpasses some of the supervised methods, demonstrating our debiasing framework’s effectiveness.

Authors

• Xiangru Lin
• Ziyi Wu
• Guanqi Chen
• Guanbin Li Sun Yat-sen University GuangDong Province Key Laboratory of Information Security Technology
• Yizhou Yu School of Computing and Data Science, The University of Hong Kong

Keywords

No keywords are indexed for this paper.