Related papers: MixTex: Unambiguous Recognition Should Not Rely So…

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…

We study the problem of recognizing structured text, i.e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing. A biased recognizer…

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…

This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in…

Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, previous mixup-based methods have an underlying prior…

In this paper, we present MixRep, a simple and effective data augmentation strategy based on mixup for low-resource ASR. MixRep interpolates the feature dimensions of hidden representations in the neural network that can be applied to both…

A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging…

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap…

Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only…

Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix…

In this paper, we elaborate upon recipes for building multilingual representation models that are not only competitive with existing state-of-the-art models but are also more parameter efficient, thereby promoting better adoption in…

This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first leverages a couple of simple augmentation operations to…

Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize…

The extraction of text in high quality is essential for text-based document analysis tasks like Document Classification or Named Entity Recognition. Unfortunately, this is not always ensured, as poor scan quality and the resulting artifacts…

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even…

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they…