أحمد قاسم أحمد رضا حسن
-
Ensemble diversified learning for image classification with noisy labels
-
In this work, we develop a new approach for learning a deep neural network for image classification with noisy labels using ensemble diversified learning. We first partition the training set into multiple subsets with diversified image characteristics. For each subset, we train a separate deep neural network image classifier. These networks are then used to encode the input image into different feature vectors, providing diversified observations of the input image. The encoded features are then fused together and further analyzed by a decision network to produce the final classification output. We study image classification on noisy labels with and without the access to clean samples. Our extensive experimental results on the CIFAR-10 and MNIST datasets demonstrate that our proposed method outperforms existing methods by a large margin.
اخر البحوث المنشورة
-
Comparing the Effectiveness of Acceptance and Commitment Therapy and Hope Therapy on Pain Anxiety and Self-Acceptance in Patients with Leukemia
-
فردوس حميد عبو مطرود2022
-
Cyberbullying of Household Women in Iraq: A Critical Views for Prohibition of Violence
-
وليد بدر نجم عبد الله الراشدي2022
-
Reliability and Validity of the Arabic Version of the Cancer Stigma Scale
-
جاسم محمد حسن صالح الحديدي2022
-
Mediating role of operational performance among the relationship of total quality management, supply chain management and firm perfprmance
-
نور محمد احمد2022
-
IOT-MDEDTL: IOT Malware Detection based on Ensemble Deep Transfer Learning
-
ايناس امجد محمد الماني2022