A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Runmin, Feng, Mengyang, Guan, Wenlong, Wang, Dong, Lu, Huchuan, Ding, Errui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908559083569152
author Wu, Runmin
Feng, Mengyang
Guan, Wenlong
Wang, Dong
Lu, Huchuan
Ding, Errui
author_facet Wu, Runmin
Feng, Mengyang
Guan, Wenlong
Wang, Dong
Lu, Huchuan
Ding, Errui
contents Though deep learning techniques have made great progress in salient object detection recently, the predicted saliency maps still suffer from incomplete predictions due to the internal complexity of objects and inaccurate boundaries caused by strides in convolution and pooling operations. To alleviate these issues, we propose to train saliency detection networks by exploiting the supervision from not only salient object detection, but also foreground contour detection and edge detection. First, we leverage salient object detection and foreground contour detection tasks in an intertwined manner to generate saliency maps with uniform highlight. Second, the foreground contour and edge detection tasks guide each other simultaneously, thereby leading to precise foreground contour prediction and reducing the local noises for edge prediction. In addition, we develop a novel mutual learning module (MLM) which serves as the building block of our method. Each MLM consists of multiple network branches trained in a mutual learning manner, which improves the performance by a large margin. Extensive experiments on seven challenging datasets demonstrate that the proposed method has delivered state-of-the-art results in both salient object detection and edge detection.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21363
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised
Wu, Runmin
Feng, Mengyang
Guan, Wenlong
Wang, Dong
Lu, Huchuan
Ding, Errui
Computer Vision and Pattern Recognition
Artificial Intelligence
Though deep learning techniques have made great progress in salient object detection recently, the predicted saliency maps still suffer from incomplete predictions due to the internal complexity of objects and inaccurate boundaries caused by strides in convolution and pooling operations. To alleviate these issues, we propose to train saliency detection networks by exploiting the supervision from not only salient object detection, but also foreground contour detection and edge detection. First, we leverage salient object detection and foreground contour detection tasks in an intertwined manner to generate saliency maps with uniform highlight. Second, the foreground contour and edge detection tasks guide each other simultaneously, thereby leading to precise foreground contour prediction and reducing the local noises for edge prediction. In addition, we develop a novel mutual learning module (MLM) which serves as the building block of our method. Each MLM consists of multiple network branches trained in a mutual learning manner, which improves the performance by a large margin. Extensive experiments on seven challenging datasets demonstrate that the proposed method has delivered state-of-the-art results in both salient object detection and edge detection.
title A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.21363