Semi-supervised Active Salient Object Detection

Lv, Yunqiu; Liu, Bowen; Zhang, Jing; Dai, Yuchao; Li, Aixuan; Zhang, Tong

doi:10.1016/j.patcog.2021.108364

Cited by 20 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[13] argued that there is a limitation to precise labeling of trainingpurpose datasets, and proposed a data uncertainty loss function that overcomes the limitation as an alternative. [27] used an adversarial decoder with a saliency network to extract a confidence map representing model uncertainty and use it for learning. [12] estimated data uncertainty through prediction inaccuracy based on the difference between the prediction map and GT, which is known as the most general approach for estimating data uncertainty.…”

Section: Related Workmentioning

confidence: 99%

Data and Model Uncertainty Aware Salient Object Detection

Lee,

Song

2024

IEEE Access

View full text Add to dashboard Cite

In general, salient object detection (SOD) datasets have ambiguity due to annotation accuracy and human subjectivity in determining saliency. Since this data uncertainty causes inaccurate prediction, many techniques tackling data uncertainty have been proposed so far. Previous works estimated data uncertainty in terms of predictive inaccuracy and adjusted the learning contribution so that a given model can focus more on specific data. However, inaccurate predictions can occur due to not only data uncertainty but also model uncertainty in which the model does not fully explain the data. As a result, a region that is inaccurately predicted due to model uncertainty is considered a region with high data uncertainty, resulting in insufficient learning. To solve this problem, we propose a novel uncertainty-aware learning scheme where model uncertainty is decomposed from prediction uncertainty and it is minimized. Also, we propose a refinement method to further improve performance by correcting the prediction result using data uncertainty in the inference step. The proposed uncertainty-aware method excludes data uncertainty from learning step and inference step more effectively, making the model more accurately detect salient object(s). The experimental results prove that the proposed method achieves state-of-the-art performance on several SOD datasets and qualitatively detects salient objects more accurately than the prior arts. The code will be uploaded on Github.

show abstract

Section: Related Workmentioning

confidence: 99%

Data and Model Uncertainty Aware Salient Object Detection

Lee,

Song

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The exploration of an informative latent space enhances confidence estimation accuracy, facilitating the effective utilization of unlabeled training data. ASOD [27] is an active learning framework for semisupervised SOD, desigened to optimize network performace with minimal annotation costs. ASOD introduces adversarial learning and unsupervised feature representation through a Variational Autoencoder (VAE) to identify discriminative and representative samples for addition to the labeled pool.…”

Section: Semi-supervised Salient Object Detectionmentioning

confidence: 99%

A Multi-View Integrated Ensemble for the Background Discrimination of Semi-Supervised Semantic Segmentation

Gwak,

Jeong,

Kim

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The key to semi-supervised semantic segmentation is to assign the appropriate pseudo-label to the pixels of unlabeled images. Recently, various approaches to consistency-based training and the filtering of reliable pseudo-labels have shown remarkable results. Nonetheless, there are still issues to be addressed. We find that recent approaches have specific problems in common. In pseudo-labels for training unlabeled images, we confirm that false foreground class pseudo-labels are mostly caused by background class confusion, not confusion between different foreground classes. To solve this problem, we propose a foreground and background discrimination model for semi-supervised semantic segmentation. Our proposed model is trained using a novel approach called multi-view integrated ensemble (MVIE) via output perturbation. Experimental results in various partition protocols show that our approach outperforms the existing state of the art (SOTA) in binary prediction on unlabeled data, and the segmentation model trained with the help of our model outperforms existing models.

show abstract

“…Thus, uncorrected (by experts) machine-generated annotations are likely to lead to incorrect predictions being reinforced during network optimization, which in turn leads to worse task performance at test time. To address this problem, a semi-supervised active learning (SSAL) strategy is sometimes used, which generally uses a pipeline of (i) query function for selecting “informative” samples from the annotation-free data pools, (ii) forwarding those to oracle annotators for generating ground truth annotation, and subsequently (iii) adding those new annotated data to the training data pool ( Zhao et al, 2021 , Gao et al, 2020b , Calma et al, 2018 , Lv et al, 2022 , Bull et al, 2018 ). However, such oracle annotation systems share limitations similar to those of expert supervision in medical imaging applications, namely, the time and labor requirements placed upon expert radiologists who are rarely available or interested in such manual dense annotation tasks, as well as the poor intra- and inter-annotator reproducibility.…”

Section: Introductionmentioning

confidence: 99%