Classifier‐Guided Visual Correction of Noisy Labels for Image Classification Tasks
نویسندگان
چکیده
منابع مشابه
Image Annotation in Presence of Noisy Labels
Labels associated with social images are valuable source of information for tasks of image annotation, understanding and retrieval. These labels are often found to be noisy, mainly due to the collaborative tagging activities of users. Existing methods on annotation have been developed and verified on noise free labels of images. In this paper, we propose a novel and generic framework that explo...
متن کاملCorrection of noisy labels via mutual consistency check
Label noise can have severe negative effects on the performance of a classifier. Such noise can either arise by adversarial manipulation of the training data or from unskilled annotators frequently encountered in crowd sourcing (e.g. Amazon mechanical turk). Based on the assumption that an expert has provided some fraction of the training data, where labels can be assumed to be true, we propose...
متن کاملAuxiliary Image Regularization for Deep CNNs with Noisy Labels
Precisely-labeled data sets with sufficient amount of samples are notably important for training deep convolutional neural networks (CNNs). However, many of the available real-world data sets contain erroneously labeled samples and the error in labels of training sample makes it a daunting task to learn a well-performing deep CNN model. In this work, we consider the problem of training a deep C...
متن کاملLearning of Classification Models from Noisy Soft-Labels
We develop and test a new classification model learning algorithm that relies on the soft-label information and that is able to learn classification models more rapidly and with a smaller number of labeled instances than existing approaches.
متن کاملDomain adaptation networks for noisy image classification
In this thesis, we propose a novel semi-supervised clean-noisy datasets adaptation algorithm. We transfer the knowledge learned on clean images to unlabeled noise-distorted ones. This modification on standard deep networks produce stable classification performance on all distortion levels, which brings benefit to real-world cases. Specifically, we propose a strategy to jointly learn a shared fe...
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: Computer Graphics Forum
سال: 2020
ISSN: 0167-7055,1467-8659
DOI: 10.1111/cgf.13973