Related papers: DoubleMix: Simple Interpolation-Based Data Augment…
Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…
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…
This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for…
Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to…
Mixup is an effective data augmentation method that generates new augmented samples by aggregating linear combinations of different original samples. However, if there are noises or aberrant features in the original samples, Mixup may…
Data augmentation has shown its effectiveness in resolving the data-hungry problem and improving model's generalization ability. However, the quality of augmented data can be varied, especially compared with the raw/original data. To boost…
Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup methods have improved previous static policies effectively…
Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…
In this work, we present a simple and elegant approach to language modeling for bilingual code-switched text. Since code-switching is a blend of two or more different languages, a standard bilingual language model can be improved upon by…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
The Mixup method (Zhang et al. 2018), which uses linearly interpolated data, has emerged as an effective data augmentation tool to improve generalization performance and the robustness to adversarial examples. The motivation is to curtail…
We study the problem of robust data augmentation for regression tasks in the presence of noisy data. Data augmentation is essential for generalizing deep learning models, but most of the techniques like the popular Mixup are primarily…
Generic object detection algorithms have proven their excellent performance in recent years. However, object detection on underwater datasets is still less explored. In contrast to generic datasets, underwater images usually have color…
The increasing size and complexity of pre-trained language models have demonstrated superior performance in many applications, but they usually require large training datasets to be adequately trained. Insufficient training sets could…
Leveraging unlabelled data through weak or distant supervision is a compelling approach to developing more effective text classification models. This paper proposes a simple but effective data augmentation method, which leverages the idea…
Large-scale, big-variant, high-quality data are crucial for developing robust and successful deep-learning models for medical applications since they potentially enable better generalization performance and avoid overfitting. However, the…
Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal…
For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…
Quantitative measurements produced by mass spectrometry proteomics experiments offer a direct way to explore the role of proteins in molecular mechanisms. However, analysis of such data is challenging due to the large proportion of missing…