Related papers: Data Fine-tuning
In the last years decision-focused learning framework, also known as predict-and-optimize, have received increasing attention. In this setting, the predictions of a machine learning model are used as estimated cost coefficients in the…
Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation…
Deep learning has a wide range of applications in industrial scenario, but reducing false alarm (FA) remains a major difficulty. Optimizing network architecture or network parameters is used to tackle this challenge in academic circles,…
Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…
Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…
Although supervised finetuning (SFT) has emerged as an essential technique to align large language models with humans, it is considered superficial, with style learning being its nature. At the same time, recent works indicate the…
The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…
Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training.…
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…
Latent diffusion models can be used as a powerful augmentation method to artificially extend datasets for enhanced training. To the human eye, these augmented images look very different to the originals. Previous work has suggested to use…
Data obfuscation deals with the problem of masking a data-set in such a way that the utility of the data is maximized while minimizing the risk of the disclosure of sensitive information. To protect data we address some ways that may as…
Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper, we propose to optimize image recognition models and data…
Machine learning systems are often trained using data collected from historical decisions. If past decisions were biased, then automated systems that learn from historical data will also be biased. We propose a black-box approach to…
Recent studies have shown that Machine Learning (ML) models can exhibit bias in real-world scenarios, posing significant challenges in ethically sensitive domains such as healthcare. Such bias can negatively affect model fairness, model…
Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to…
In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by fine-tuning. The problem assumes a realistic scenario for face identification, where only a small number of face images is given for…
With the proliferation of algorithmic decision-making, increased scrutiny has been placed on these systems. This paper explores the relationship between the quality of the training data and the overall fairness of the models trained with…
Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…
Artificial neural networks have proven to be extremely useful models that have allowed for multiple recent breakthroughs in the field of Artificial Intelligence and many others. However, they are typically regarded as black boxes, given how…