Related papers: SUMix: Mixup with Semantic and Uncertain Informati…
We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level…
Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we…
In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…
Data augmentation is an essential technique for improving recognition accuracy in object recognition using deep learning. Methods that generate mixed data from multiple data sets, such as mixup, can acquire new diversity that is not…
Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs…
To address the issues of MixUp and its variants (e.g., Manifold MixUp) in image classification tasks-namely, their neglect of mixing within the same class (intra-class mixup) and their inadequacy in enhancing intra-class cohesion through…
Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation,…
Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is…
We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions…
While deep AUC maximization (DAM) has shown remarkable success on imbalanced medical tasks, e.g., chest X-rays classification and skin lesions classification, it could suffer from severe overfitting when applied to small datasets due to its…
It is expensive and time-consuming to collect sufficient labeled data to build human activity recognition (HAR) models. Training on existing data often makes the model biased towards the distribution of the training data, thus the model…
Data mixing augmentation has been widely applied to improve the generalization ability of deep neural networks. Recently, offline data mixing augmentation, e.g. handcrafted and saliency information-based mixup, has been gradually replaced…
Probabilistic mixture models have been widely used for different machine learning and pattern recognition tasks such as clustering, dimensionality reduction, and classification. In this paper, we focus on trying to solve the most common…
Deep image classifiers often perform poorly when training data are heavily class-imbalanced. In this work, we propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and…
Deep learning-based methods have achieved considerable success on single image dehazing in recent years. However, these methods are often subject to performance degradation when domain shifts are confronted. Specifically, haze density gaps…
Semi-supervised learning via learning from limited quantities of labeled data has been investigated as an alternative to supervised counterparts. Maximizing knowledge gains from copious unlabeled data benefit semi-supervised learning…
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…
Recently, machine learning-based semantic segmentation algorithms have demonstrated their potential to accurately segment regions and contours in medical images, allowing the precise location of anatomical structures and abnormalities.…
We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in…
Mixup is a popular data augmentation method, with many variants subsequently proposed. These methods mainly create new examples via convex combination of random data pairs and their corresponding one-hot labels. However, most of them adhere…