MTCSNet: Mean Teachers Cross-Supervision Network for Semi-Supervised Cloud Detection
نویسندگان
چکیده
Cloud detection methods based on deep learning depend large and reliable training datasets to achieve high accuracy. There will be a significant impact their performance, however when the data are insufficient or label quality is low. Thus, alleviate this problem, semi-supervised cloud method, named mean teacher cross-supervision network (MTCSNet) proposed. This method enforces both consistency accuracy two student branches, which perturbed with different initializations, for same input image. For each of respective used generate high-quality pseudo labels, constructed using an exponential moving average (EMA). A one-hot label, produced by one branch, supervises other branch standard cross-entropy loss, vice versa. To incorporate additional prior information into model, presented uses near-infrared bands instead red as model inputs injects strong augmentations unlabeled images fed model. induces learn richer representations ensure constraints predictions image across batches. attain more refined equilibrium between supervised loss in process, proposed learns optimal weights homoscedastic uncertainty, thus effectively exploiting advantages tasks elevating overall performance. Experiments SPARCS GF1-WHU public show that outperforms several state-of-the-art algorithms only limited number labeled samples available.
منابع مشابه
Semi-Supervised Mean Fields
A novel semi-supervised learning approach based on statistical physics is proposed in this paper. We treat each data point as an Ising spin and the interaction between pairwise spins is captured by the similarity between the pairwise points. The labels of the data points are treated as the directions of the corresponding spins. In semi-supervised setting, some of the spins have fixed directions...
متن کاملSemi-supervised Random Forest for Intrusion Detection Network
In order to protect valuable computer systems, network data needs to be analyzed and classified so that possible network intrusions can be detected. Machine learning techniques have been used to classify network data. For supervised machine learning methods, they can achieve high accuracy at classifying network data as normal or malicious, but they require the availability of fully labeled data...
متن کاملSemi-supervised Statistical Approach for Network Anomaly Detection
Intrusion Detection Systems (IDS) have become a very important defense measure against security threats. In recent years, computer networks are widely deployed for critical and complex systems, which make them more vulnerable to network attacks. In this paper, we propose a two-stage Semi-supervised Statistical approach for Anomaly Detection (SSAD). The first stage of SSAD aims to build a probab...
متن کاملWeak Supervision for Semi-supervised Topic Modeling via Word Embeddings
Semi-supervised algorithms have been shown to improve the results of topic modeling when applied to unstructured text corpora. However, sufficient supervision is not always available. This paper proposes a new process, Weak+, suitable for use in semi-supervised topic modeling via matrix factorization, when limited supervision is available. This process uses word embeddings to provide additional...
متن کاملMean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change only once per epoch, Temporal Ensembling becomes unwieldy when learning large...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2023
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs15082040