Regularizing Deep Networks with Semantic Data Augmentation
نویسندگان
چکیده
منابع مشابه
Learning Deep Sigmoid Belief Networks with Data Augmentation
Deep directed generative models are developed. The multi-layered model is designed by stacking sigmoid belief networks, with sparsity-encouraging priors placed on the model parameters. Learning and inference of layer-wise model parameters are implemented in a Bayesian setting. By exploring the idea of data augmentation and introducing auxiliary Pólya-Gamma variables, simple and efficient Gibbs ...
متن کاملRegularizing Prediction Entropy Enhances Deep Learning with Limited Data
Many supervised learning problems require learning with small amounts of training data, since constructing large training datasets could be impractical due to cost, labor, or unavailability of data. For such tasks, constructing deep learning approaches that generalize to new data is difficult. In this paper, we demonstrate the effectiveness of using entropy as a regularizer on image classificat...
متن کاملMusic Transcription by Deep Learning with Data and "Artificial Semantic" Augmentation
In this progress paper the previous results of the single note recognition by deep learning are presented. The several ways for data augmentation and “artificial semantic” augmentation are proposed to enhance efficiency of deep learning approaches for monophonic and polyphonic note recognition by increase of dimensions of training data, their lossless and lossy transformations.
متن کاملRegularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
Overfitting is one of the most critical challenges in deep neural networks, and there are various types of regularization methods to improve generalization performance. Injecting noises to hidden units during training, e.g., dropout, is known as a successful regularizer, but it is still not clear enough why such training techniques work well in practice and how we can maximize their benefit in ...
متن کاملRegularizing Deep Hashing Networks Using GAN Generated Fake Images
Recently, deep-networks-based hashing (deep hashing) has become a leading approach for large-scale image retrieval. It aims to learn a compact bitwise representation for images via deep networks, so that similar images are mapped to nearby hash codes. Since a deep network model usually has a large number of parameters, it may probably be too complicated for the training data we have, leading to...
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: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2021
ISSN: 0162-8828,2160-9292,1939-3539
DOI: 10.1109/tpami.2021.3052951