Related papers: MixText: Linguistically-Informed Interpolation of …
Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data…
Text classification, a core component of task-oriented dialogue systems, attracts continuous research from both the research and industry community, and has resulted in tremendous progress. However, existing method does not consider the use…
We propose TextManiA, a text-driven manifold augmentation method that semantically enriches visual feature spaces, regardless of class distribution. TextManiA augments visual data with intra-class semantic perturbation by exploiting…
We propose a novel semi-supervised learning (SSL) method that adopts selective training with pseudo labels. In our method, we generate hard pseudo-labels and also estimate their confidence, which represents how likely each pseudo-label is…
The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient…
Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…
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…
Mixup is a widely adopted strategy for training deep networks, where additional samples are augmented by interpolating inputs and labels of training pairs. Mixup has shown to improve classification performance, network calibration, and…
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more…
Deep learning-based models, when trained in a fully-supervised manner, can be effective in performing complex image analysis tasks, although contingent upon the availability of large labeled datasets. Especially in the medical imaging…
Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in…
In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…
A common classification task situation is where one has a large amount of data available for training, but only a small portion is annotated with class labels. The goal of semi-supervised training, in this context, is to improve…
Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and…
This paper presents a supervised mixing augmentation method termed SuperMix, which exploits the salient regions within input images to construct mixed training samples. SuperMix is designed to obtain mixed images rich in visual features and…
Using large training datasets enhances the generalization capabilities of neural networks. Semi-supervised learning (SSL) is useful when there are few labeled data and a lot of unlabeled data. SSL methods that use data augmentation are most…
Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…
Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency…
Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…
Small sample instance segmentation is a very challenging task, and many existing methods follow the training strategy of meta-learning which pre-train models on support set and fine-tune on query set. The pre-training phase, which is highly…