Related papers: Pathways to Leverage Transcompiler based Data Augm…

Data limitation is one of the most common issues in training machine learning classifiers for medical applications. Due to ethical concerns and data privacy, the number of people that can be recruited to such experiments is generally…

Surface crack segmentation poses a challenging computer vision task as background, shape, colour and size of cracks vary. In this work we propose optimized deep encoder-decoder methods consisting of a combination of techniques which yield…

While deep learning methods have shown great success in medical image analysis, they require a number of medical images to train. Due to data privacy concerns and unavailability of medical annotators, it is oftentimes very difficult to…

The generalization capability of deepfake detectors is critical for real-world use. Data augmentation via synthetic fake face generation effectively enhances generalization, yet current SoTA methods rely on fixed strategies-raising a key…

This paper investigates source code similarity detection using a transformer model augmented with an execution-derived signal. We extend GraphCodeBERT with an explicit, low-dimensional behavioral feature that captures observable agreement…

Data augmentation is essential to achieve state-of-the-art performance in many deep learning applications. However, the most effective augmentation techniques become computationally prohibitive for even medium-sized datasets. To address…

Parallel programs in high performance computing (HPC) continue to grow in complexity and scale in the exascale era. The diversity in hardware and parallel programming models make developing, optimizing, and maintaining parallel software…

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary LLMs. However, many languages written in non-Latin scripts…

Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typically rely on source code alone, overlooking contextual…

Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective)…

Most pre-trained Vision-Language (VL) models and training data for the downstream tasks are only available in English. Therefore, multilingual VL tasks are solved using cross-lingual transfer: fine-tune a multilingual pre-trained model or…

Data augmentation has been shown to effectively improve the performance of multimodal machine learning models. This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities.…

Recent advances in machine learning (ML) and computer vision tools have enabled applications in a wide variety of arenas such as financial analytics, medical diagnostics, and even within the Department of Defense. However, their widespread…

Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotations and flips,…

Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little surface similarity. Although large language models (LLMs) have shown promise for semantic…

Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and…

Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or…

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.…

Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even when trained without parallel data. Yet, despite the fact that the amount of training data is gigantic, they still…

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…