DeepAI AI Chat
Log In Sign Up

To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection

by   Yongri Piao, et al.
Dalian University of Technology

Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate. In this work, 1) we propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions, liberating the saliency network from error-prone propagation caused by pseudo labels. 2) we prove that even a much smaller dataset (merely 1.8 models to achieve better performance as well as generalizability. This sheds new light on the development of WSOD and encourages more contributions to the community. Comprehensive experiments demonstrate that our method outperforms all the existing WSOD methods by adopting the self-calibrated strategy only. Steady improvements are further achieved by training on the proposed dataset. Additionally, our method achieves 94.7 methods on average. And what is more, the fully supervised models adopting our predicted results as "ground truths" achieve successful results (95.6 BASNet and 97.3 time for pixel-level annotation.


page 1

page 2

page 3

page 6

page 7


MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection

Weakly supervised salient object detection (WSOD) targets to train a CNN...

Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence

Sparse labels have been attracting much attention in recent years. Howev...

Weakly-Supervised Salient Object Detection Using Point Supervison

Current state-of-the-art saliency detection models rely heavily on large...

Uncertainty-Aware Deep Calibrated Salient Object Detection

Existing deep neural network based salient object detection (SOD) method...

Weakly Supervised Salient Object Detection Using Image Labels

Deep learning based salient object detection has recently achieved great...

Weakly-supervised Salient Instance Detection

Existing salient instance detection (SID) methods typically learn from p...

Learning to Detect Instance-level Salient Objects Using Complementary Image Labels

Existing salient instance detection (SID) methods typically learn from p...