人工智能
计算机科学
一致性(知识库)
计算机视觉
突出
模式识别(心理学)
对象(语法)
目标检测
数学
作者
Liyuan Chen,Wei Liu,Hua Wang,Sang-Woon Jeon,Yunliang Jiang,Zheng Zheng
标识
DOI:10.1109/tcsvt.2025.3539471
摘要
This paper presents a novel approach that leverages two models to integrate features from numerous unlabeled images, addressing the challenge of semi-supervised salient object detection (SSOD). Unlike conventional methods that rely on selecting high-quality pseudo labels, our method identifies the model that produces consistent predictions for original images and their color transformation versions from two models to infer reliable pseudo labels for all unlabeled images, improving the diversity of the training set. Specifically, we propose adaptive selection indicators to quantify prediction differences and guide the updates of the two models using the unlabeled set alternatively. Initially, two models used in our framework are trained on the labeled set. Once the adaptive selection indicator conditions are satisfied, one model is designated as the proxy, generating pseudo labels, while the other serves as the saliency model, which is further trained using these pseudo labels. Subsequently, the updated saliency model optimizes the proxy model’s parameters according to another adaptive selection indicator. Experimental results and ablation studies on six benchmark salient object detection datasets confirm the effectiveness and robustness of our method. Our approach achieves performance comparable to recent fully supervised methods while using only one eighth of the labeled data, demonstrating its potential for efficient and scalable SSOD. This paper is publicly available at https://github.com/Liyuan0905/CATNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI