Related papers: Data Interpolating Prediction: Alternative Interpr…
Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the…
We propose Duality Gap KIP (DGKIP), an extension of the Kernel Inducing Points (KIP) method for dataset distillation. While existing dataset distillation methods often rely on bi-level optimization, DGKIP eliminates the need for such…
Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the…
While deep neural networks show great performance on fitting to the training distribution, improving the networks' generalization performance to the test distribution and robustness to the sensitivity to input perturbations still remain as…
Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…
Time series observations can be seen as realizations of an underlying dynamical system governed by rules that we typically do not know. For time series learning tasks, we need to understand that we fit our model on available data, which is…
We show that the effectiveness of the well celebrated Mixup [Zhang et al., 2018] can be further improved if instead of using it as the sole learning objective, it is utilized as an additional regularizer to the standard cross-entropy loss.…
As a part of the Data-Centric AI Competition, we propose a data-centric approach to improve the diversity of the training samples by iterative sampling. The method itself relies strongly on the fidelity of augmented samples and the…
For many use cases, combining information from different datasets can be of interest to improve a machine learning model's performance, especially when the number of samples from at least one of the datasets is small. However, a potential…
In this paper, we approach the problem of uncertainty quantification in deep learning through a predictive framework, which captures uncertainty in model parameters by specifying our assumptions about the predictive distribution of unseen…
Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit…
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.…
Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…
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…
Data augmentation is a widely used technique in many machine learning tasks, such as image classification, to virtually enlarge the training dataset size and avoid overfitting. Traditional data augmentation techniques for image…
Mixed-integer programming (MIP) technology offers a generic way of formulating and solving combinatorial optimization problems. While generally reliable, state-of-the-art MIP solvers base many crucial decisions on hand-crafted heuristics,…
Mixed sample data augmentation strategies are actively used when training deep neural networks (DNNs). Recent studies suggest that they are effective at various tasks. However, the impact of mixed sample data augmentation on model…
Real-world binary classification tasks are in many cases imbalanced, where the minority class is much smaller than the majority class. This skewness is challenging for machine learning algorithms as they tend to focus on the majority and…
Imbalanced datasets present a significant challenge for machine learning models, often leading to biased predictions. To address this issue, data augmentation techniques are widely used in natural language processing (NLP) to generate new…
Text classification tasks often encounter few shot scenarios with limited labeled data, and addressing data scarcity is crucial. Data augmentation with mixup has shown to be effective on various text classification tasks. However, most of…