Related papers: A Unified Analysis of Mixed Sample Data Augmentati…
The distribution shifts between training and test data typically undermine the performance of models. In recent years, lots of work pays attention to domain generalization (DG) where distribution shifts exist, and target data are unseen.…
Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…
Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on…
Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based…
The removal of carefully-selected examples from training data has recently emerged as an effective way of improving the robustness of machine learning models. However, the best way to select these examples remains an open question. In this…
Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer from severe data scarcity and high annotation costs, severely…
Data augmentation is arguably the most important regularization technique commonly used to improve generalization performance of machine learning models. It primarily involves the application of appropriate data transformation operations to…
Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD. In this work, we report a…
With the increasing utilization of deep learning in outdoor settings, its robustness needs to be enhanced to preserve accuracy in the face of distribution shifts, such as compression artifacts. Data augmentation is a widely used technique…
Data augmentation is one of the regularization strategies for the training of deep learning models, which enhances generalizability and prevents overfitting, leading to performance improvement. Although researchers have proposed various…
Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…
Data augmentation, by the introduction of auxiliary variables, has become an ubiquitous technique to improve convergence properties, simplify the implementation or reduce the computational time of inference methods such as Markov chain…
Inspired by the great success of Deep Neural Networks (DNNs) in natural language processing (NLP), DNNs have been increasingly applied in source code analysis and attracted significant attention from the software engineering community. Due…
We propose the AdaPtive Noise Augmentation (PANDA) procedure to regularize the estimation and inference of generalized linear models (GLMs). PANDA iteratively optimizes the objective function given noise augmented data until convergence to…
Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets. Consequently, a recent trend is to adopt AutoML technique…
Given the special situation of modeling gigapixel images, multiple instance learning (MIL) has become one of the most important frameworks for Whole Slide Image (WSI) classification. In current practice, most MIL networks often face two…
We present a unified theorem for the convergence analysis of stochastic gradient algorithms for minimizing a smooth and convex loss plus a convex regularizer. We do this by extending the unified analysis of Gorbunov, Hanzely \& Richt\'arik…
Parallelism is a ubiquitous method for accelerating machine learning algorithms. However, theoretical analysis of parallel learning is usually done in an algorithm- and protocol-specific setting, giving little insight about how changes in…
The growing adoption of spectrum-aware matrix-valued optimizers such as Muon and Shampoo in deep learning motivates a systematic study of their generalization properties and, in particular, when they might outperform competitive algorithms.…
This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative models as an additional dataset for classification with small…